© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97409
    Prev
    Next
    INDEX
    Explanations

    legal cases/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įä¿¡
    -0.26
    datal
    -0.26
    è¶Ĭè¿ĩ
    -0.25
    HttpException
    -0.25
    躺çĿĢ
    -0.24
    ész
    -0.24
    åľ°çľĭçĿĢ
    -0.24
    å¸IJ篷
    -0.23
    rong
    -0.23
    EO
    -0.23
    POSITIVE LOGITS
    æ¯ıæĹ¥
    0.28
    abelle
    0.26
     Starr
    0.26
    olini
    0.26
    omin
    0.24
    åıijå±ķæĪĺçķ¥
    0.24
    ado
    0.24
    iano
    0.24
     McDon
    0.23
    omain
    0.23
    Activations Density 0.014%

    No Known Activations