© 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. 63604
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    nameof
    -0.27
     balances
    -0.27
    bla
    -0.26
     COVER
    -0.26
    icator
    -0.26
     mee
    -0.25
    è¡¡
    -0.24
    renc
    -0.24
    cko
    -0.24
    éĢł
    -0.24
    POSITIVE LOGITS
     three
    0.40
     five
    0.39
    -three
    0.39
     trois
    0.38
     four
    0.37
    äºĶ个
    0.36
    five
    0.36
     quatre
    0.35
    åıªæľīä¸Ģ个
    0.35
    three
    0.35
    Activations Density 64.046%

    No Known Activations