© 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. 14-TRANSCODER-HP
    7. 41403
    Prev
    Next
    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľįåĬ¡æľºæŀĦ
    -0.10
    worth
    -0.09
    aghan
    -0.08
    å·¥ç¨ĭæĸ½å·¥
    -0.08
    æīĢåľ¨çļĦ
    -0.08
     spirits
    -0.08
    edException
    -0.08
     courtroom
    -0.08
    åĨ·æ¼ł
    -0.08
    gne
    -0.08
    POSITIVE LOGITS
    å©¿
    0.10
    西äºļ
    0.09
     Ing
    0.09
    Ñħод
    0.09
    ä¸īæĿ¡
    0.08
    Ñīи
    0.08
    çĶ«
    0.08
     Sah
    0.08
    åįģäºĮæĿ¡
    0.08
    éĩįè¦ģ
    0.08
    Activations Density 2.053%

    No Known Activations