© 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. 50646
    Prev
    Next
    INDEX
    Explanations

    Appeals

    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
    ぬ
    -0.08
    直观
    -0.07
    -team
    -0.07
    为目的
    -0.07
    太大
    -0.07
    妲
    -0.07
    决胜
    -0.07
    等到
    -0.07
    馃
    -0.06
    inspace
    -0.06
    POSITIVE LOGITS
     requesting
    0.08
     neger
    0.07
    翻译
    0.07
    拆
    0.07
     discontinued
    0.07
    })
    0.07
     Afghanistan
    0.07
     рег
    0.07
    (down
    0.07
     infographic
    0.07
    Activations Density 0.000%

    No Known Activations