© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29790
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Not in Any Lists

    No Comments

    Negative Logits
     passive
    -0.31
    被åĬ¨
    -0.29
     glob
    -0.28
    ä¸ĢåĪĨéĴŁ
    -0.26
     interacting
    -0.25
    %/
    -0.25
     channels
    -0.24
     fuse
    -0.24
     fusion
    -0.24
     uplifting
    -0.24
    POSITIVE LOGITS
    ä¿ĿæĮģ
    0.28
    åĽ´
    0.28
    ieÅĦ
    0.27
    å¢ĵ
    0.26
    EMS
    0.25
    åı£åij³
    0.25
    产éĩı
    0.25
     comer
    0.25
     Bien
    0.25
    é¢Ĭ
    0.25
    Activations Density 1.699%

    No Known Activations