© 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. 13906
    Prev
    Next
    INDEX
    Explanations

    feedback loops

    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
    _ITER
    -0.08
     councils
    -0.07
    ,"\
    -0.07
    -panel
    -0.07
     interstate
    -0.07
    -0.06
    濑
    -0.06
    коль
    -0.06
    idents
    -0.06
    داول
    -0.06
    POSITIVE LOGITS
    'u
    0.07
     poke
    0.07
    ategory
    0.06
     לוקח
    0.06
     segunda
    0.06
    	fn
    0.06
    -install
    0.06
    (rename
    0.06
    没有太大
    0.06
     Greene
    0.06
    Activations Density 0.088%

    No Known Activations