© 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. 141942
    Prev
    Next
    INDEX
    Explanations

    par

    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
    姹
    -0.26
    ðŁijĩ
    -0.26
    请è¾ĵåħ¥
    -0.25
    ifu
    -0.25
    hya
    -0.24
    --*/↵
    -0.24
    åĩ¹
    -0.24
    =?,
    -0.24
    Contin
    -0.24
     sing
    -0.24
    POSITIVE LOGITS
    aths
    0.28
     Lagos
    0.26
    ematics
    0.26
    naire
    0.26
    get
    0.25
     viewed
    0.25
     Logan
    0.25
    leg
    0.25
    ath
    0.25
    aux
    0.25
    Activations Density 24.104%

    No Known Activations