© 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. 11-RESID-POST-AA
    11. 113498
    Prev
    Next
    INDEX
    Explanations

    school

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    粳
    -0.07
     hamstring
    -0.07
    $pdf
    -0.07
     ws
    -0.07
     inaugural
    -0.07
    ใ
    -0.07
    现身
    -0.07
    	REQUIRE
    -0.07
    -java
    -0.07
    郑州
    -0.07
    POSITIVE LOGITS
     complexes
    0.07
    ,eg
    0.07
    냈
    0.07
    .lineTo
    0.06
     matière
    0.06
     estruct
    0.06
    -effects
    0.06
    藟
    0.06
     источ
    0.06
    (Output
    0.06
    Activations Density 0.001%

    No Known Activations