© 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. 12-TRANSCODER-HP
    7. 23903
    Prev
    Next
    INDEX
    Explanations

    cession

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addy
    -0.33
    วà¸Ļ
    -0.29
    éĩįä¸Ń
    -0.26
     argc
    -0.25
    客
    -0.25
    Ĥæķ°
    -0.24
    è§Ħå¾ĭ
    -0.24
    æ´İ
    -0.24
    ç¥ĵ
    -0.23
    pig
    -0.23
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½æĺ¯
    0.30
    mina
    0.29
    tings
    0.27
    éĮ
    0.27
    ç§ĺ
    0.25
     amort
    0.25
    è¿Ļä¸Ģ
    0.25
    诱åıij
    0.24
     LIVE
    0.24
    è¿ĻäºĽéĹ®é¢ĺ
    0.24
    Activations Density 0.000%

    No Known Activations