© 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. 95688
    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
    éĩĮç¨ĭç¢ij
    -0.29
    åIJĪ
    -0.28
    edor
    -0.26
    说çļĦæĺ¯
    -0.26
    åĴĮ个人
    -0.24
     Tamb
    -0.24
    clock
    -0.24
    触
    -0.24
    åIJĪçIJĨæĢ§
    -0.23
    ç»Ļä½łä»¬
    -0.23
    POSITIVE LOGITS
    .unknown
    0.28
    俯
    0.25
    åѤç«ĭ
    0.25
    汪
    0.25
    Unhandled
    0.24
     COMPUT
    0.24
     First
    0.24
     Colleges
    0.23
    //--
    0.23
    çļĦä»»åĬ¡
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.