© 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. 18769
    Prev
    Next
    INDEX
    Explanations

    Code context

    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
    خيص
    -0.07
    掖
    -0.07
     صلى
    -0.07
    iosity
    -0.07
     семей
    -0.07
    這種
    -0.07
     matrix
    -0.07
    柔性
    -0.06
    بدأ
    -0.06
    .Begin
    -0.06
    POSITIVE LOGITS
    .Thread
    0.08
    .walk
    0.08
    .getOutputStream
    0.07
    غ
    0.07
    Ｆ
    0.07
     Seriously
    0.07
     Guill
    0.07
    已久的
    0.07
    𝙍
    0.07
    涸
    0.07
    Activations Density 0.002%

    No Known Activations