© 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. 29720
    Prev
    Next
    INDEX
    Explanations

    stretchable materials

    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
    æĿĢæŃ»
    -0.33
     kill
    -0.32
    æĿĢ
    -0.29
     rav
    -0.28
    Kill
    -0.28
     cleaner
    -0.28
     killing
    -0.27
     kills
    -0.27
     clean
    -0.27
    opes
    -0.26
    POSITIVE LOGITS
     CURLOPT
    0.29
     Elastic
    0.29
     elasticity
    0.29
    ç½ijç«Ļ
    0.28
    lesh
    0.28
    eba
    0.27
    éŨæĪ·ç½ijç«Ļ
    0.27
    åĬĽ
    0.26
     MemoryStream
    0.26
    弹簧
    0.26
    Activations Density 1.094%

    No Known Activations