© 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. 30464
    Prev
    Next
    INDEX
    Explanations

    Tax

    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
     BH
    -0.27
     Pett
    -0.26
    RS
    -0.26
     enim
    -0.25
    ấu
    -0.24
    ÑĢÑĥÑĩ
    -0.24
    åĻ¬
    -0.24
    ouch
    -0.24
    abh
    -0.24
    è¦ģæĥ³
    -0.24
    POSITIVE LOGITS
    ä¸Ģå¹ħ
    0.28
    ä¸ĢéĿ¢
    0.27
    åIJĦçķĮ
    0.25
    associated
    0.24
    åIJĦæł·
    0.24
     associated
    0.23
    ention
    0.23
     technologies
    0.23
    ãģ¨ãģĦãģĨãģĵãģ¨
    0.23
    èħ¿
    0.23
    Activations Density 1.021%

    No Known Activations