© 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. 64430
    Prev
    Next
    INDEX
    Explanations

    Years and numbers

    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
    Âł
    -0.27
     whe
    -0.26
    It
    -0.26
    ro
    -0.26
    æ³¾
    -0.25
     inst
    -0.25
     Dire
    -0.25
     precip
    -0.25
    ushima
    -0.24
     cod
    -0.24
    POSITIVE LOGITS
    lettes
    0.32
    aris
    0.30
    ytt
    0.28
    nı
    0.27
    .opend
    0.26
    gı
    0.26
    /OR
    0.26
    folk
    0.26
    quisitions
    0.25
     plates
    0.25
    Activations Density 6.611%

    No Known Activations