© 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. 94560
    Prev
    Next
    INDEX
    Explanations

    [[

    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
     iam
    -0.06
    /cop
    -0.06
    苌
    -0.06
    ȯ
    -0.06
     plung
    -0.06
     intest
    -0.06
    Kenn
    -0.06
    .Scene
    -0.06
    ⓝ
    -0.06
     Teh
    -0.06
    POSITIVE LOGITS
     /.
    0.07
     highlighting
    0.07
     headline
    0.07
    market
    0.07
    cape
    0.07
    ard
    0.07
    /notification
    0.06
    방송
    0.06
    建华
    0.06
    ,!
    0.06
    Activations Density 0.001%

    No Known Activations