© 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. 20-TRANSCODER-HP
    7. 129448
    Prev
    Next
    INDEX
    Explanations

    Explanations or technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enÃŃ
    -0.28
    è¬ĩ
    -0.27
     Cour
    -0.27
    ä¸įè¿ľ
    -0.26
    urdy
    -0.26
    ung
    -0.25
    ieber
    -0.25
    emain
    -0.25
     "*.
    -0.24
    endas
    -0.24
    POSITIVE LOGITS
     tensor
    0.27
     Author
    0.25
    éĴ¢ç»ĵæŀĦ
    0.25
    æĬĵ
    0.25
     proper
    0.25
     Tensor
    0.25
    _station
    0.24
    REFER
    0.24
    åĨĻ
    0.24
    vat
    0.23
    Activations Density 19.945%

    No Known Activations