© 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. 9-TRANSCODER-HP
    7. 30295
    Prev
    Next
    INDEX
    Explanations

    End of sentences/clauses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¯¥æł¡
    -0.29
    vox
    -0.28
    CCC
    -0.28
    loser
    -0.24
    åĿŃ
    -0.23
    翻身
    -0.23
    ocaust
    -0.23
     defaultdict
    -0.23
    è¿ij
    -0.23
    èĥ½åĬĽåĴĮ
    -0.23
    POSITIVE LOGITS
     Ashe
    0.26
    finity
    0.25
    -meta
    0.25
    饮水
    0.25
    functions
    0.24
    åĨľåī¯äº§åĵģ
    0.24
    undred
    0.24
    形容
    0.23
    åIJİæİĴ
    0.23
    çģ¯
    0.23
    Activations Density 26.726%

    No Known Activations