© 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. 30-TRANSCODER-HP
    7. 96653
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¡´
    -0.30
     Dollars
    -0.25
    xo
    -0.24
    çļĦä¸ĢéĿ¢
    -0.24
    èĢĢ
    -0.24
    伸åĩº
    -0.24
    åľ¨æĪijåĽ½
    -0.24
     UNITED
    -0.23
    STER
    -0.23
     investigative
    -0.23
    POSITIVE LOGITS
    æĢ§åĪ«
    0.27
    æŁ³
    0.27
    jem
    0.24
     trần
    0.24
    æĭ¿
    0.24
     flipping
    0.23
     LC
    0.23
    éĩİå¿ĥ
    0.23
    LN
    0.23
    导èĪª
    0.23
    Activations Density 0.100%

    No Known Activations

    This feature has no known activations.