© 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. 20-TRANSCODER-HP
    7. 108435
    Prev
    Next
    INDEX
    Explanations

    Technical, mixed language content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¼Ħ
    -0.27
    andise
    -0.27
    èĥĮéĿ¢
    -0.26
     Lup
    -0.26
    tera
    -0.25
    /the
    -0.24
    £o
    -0.24
    ä¸Ģèĩ´æĢ§
    -0.24
    bomb
    -0.24
    æł¼æŀĹ
    -0.24
    POSITIVE LOGITS
    éĹ®è´£
    0.30
    åĽ´
    0.28
     :(
    0.27
     //=
    0.27
     STATUS
    0.25
    ä¸ºè¿Ľä¸ĢæŃ¥
    0.25
    çłĮ
    0.25
    æ¡¥
    0.25
     Status
    0.25
    åģļ人
    0.25
    Activations Density 1.359%

    No Known Activations