© 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. 32-TRANSCODER-HP
    7. 41762
    Prev
    Next
    INDEX
    Explanations

    computer code and music

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åİĭ
    -0.32
     Lazar
    -0.30
    sch
    -0.27
     Kill
    -0.27
    æ¿Ģ
    -0.26
     gem
    -0.26
    ä¼ij
    -0.26
    ä¸Ń央
    -0.25
    RESS
    -0.25
    _variant
    -0.25
    POSITIVE LOGITS
     listened
    0.30
    åIJ¬
    0.29
    cams
    0.27
     Listening
    0.26
    oon
    0.26
    TOT
    0.26
     BN
    0.26
     ears
    0.25
    _listener
    0.25
    composed
    0.25
    Activations Density 0.000%

    No Known Activations