© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 127066
    Prev
    Next
    INDEX
    Explanations

    corruption

    np_max-act · gemini-2.0-flash

    technical-process terms describing combining, separating, distributing, or positioning components and attributes within engineered or scientific systems.

    oai_token-act-pair · gpt-5
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Its
    -0.07
    深入了解
    -0.07
    ıyord
    -0.07
    \Repositories
    -0.07
    剖析
    -0.07
     ponto
    -0.07
     previously
    -0.06
    ᓫ
    -0.06
     Premiership
    -0.06
     quê
    -0.06
    POSITIVE LOGITS
    neck
    0.08
    arching
    0.07
    诰
    0.07
     nickname
    0.07
     flags
    0.07
    @click
    0.07
     pipes
    0.07
    席
    0.07
    领取
    0.07
    chet
    0.07
    Activations Density 6.525%

    No Known Activations