© 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. 19-RESID-POST-AA
    11. 10524
    Prev
    Next
    INDEX
    Explanations

    changes and impacts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     cf
    -0.07
     recruitment
    -0.07
    NO
    -0.07
    ᅨ
    -0.06
     odds
    -0.06
    魔王
    -0.06
     Dress
    -0.06
     creep
    -0.06
    دائرة
    -0.06
     ceiling
    -0.06
    POSITIVE LOGITS
     lifelong
    0.08
     yılında
    0.08
    (host
    0.07
     البلد
    0.07
     getState
    0.07
     backbone
    0.07
    xfb
    0.07
    yaw
    0.07
    𝚑
    0.07
     Unicorn
    0.07
    Activations Density 0.177%

    No Known Activations