© 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. 141787
    Prev
    Next
    INDEX
    Explanations

    technical reports

    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
    èįĴ
    -0.32
    edith
    -0.28
    ssp
    -0.26
    iciar
    -0.26
    /cop
    -0.26
    EDIUM
    -0.25
    agini
    -0.25
    åĿı
    -0.25
     consultants
    -0.25
     ogl
    -0.25
    POSITIVE LOGITS
    gent
    0.25
    neck
    0.24
    ruz
    0.24
    urate
    0.24
     segregation
    0.24
    ëłģ
    0.24
    å¸ĸ
    0.24
    âĢ
    0.23
    orama
    0.23
    éĽ¢
    0.23
    Activations Density 15.243%

    No Known Activations