© 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. 107735
    Prev
    Next
    INDEX
    Explanations

    communication and technology

    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
    ewise
    -0.30
    æ´¾
    -0.29
     Aur
    -0.27
    @[
    -0.27
     breached
    -0.25
     Charl
    -0.24
     Orchard
    -0.24
    ç»Ń
    -0.24
     seguir
    -0.23
    çļĦæĢĿæĥ³
    -0.23
    POSITIVE LOGITS
    epend
    0.29
     fades
    0.27
    eken
    0.26
    館
    0.25
    town
    0.24
    -faced
    0.24
    Moment
    0.24
    ä¸¤å¼ł
    0.23
    ή
    0.23
    idth
    0.23
    Activations Density 2.656%

    No Known Activations