© 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. 63772
    Prev
    Next
    INDEX
    Explanations

    questions/statements

    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
     either
    -0.32
    both
    -0.30
     both
    -0.30
    either
    -0.29
    ax
    -0.28
    åīįèĢħ
    -0.27
    æĹ¢çĦ¶
    -0.26
    æĹ¥èµ·
    -0.26
     zarówno
    -0.25
    ä¸į论æĺ¯
    -0.25
    POSITIVE LOGITS
     Chronicle
    0.28
    åĮIJ
    0.28
    iaz
    0.27
    iembre
    0.26
    ÅĽcie
    0.26
     maur
    0.26
    ä¸ı
    0.25
    unal
    0.25
    gress
    0.25
    perial
    0.25
    Activations Density 64.871%

    No Known Activations