© 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. 31-TRANSCODER-HP
    7. 18471
    Prev
    Next
    INDEX
    Explanations

    Clothing and design

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trait
    -0.28
     Grant
    -0.27
    éĢĴ
    -0.26
    ç»į
    -0.26
    éĻĮ
    -0.26
    ÑģеÑĢ
    -0.25
     Trait
    -0.25
     grant
    -0.25
     treaty
    -0.24
    abbr
    -0.24
    POSITIVE LOGITS
     fashion
    0.37
     tail
    0.29
    æŶè£ħ
    0.28
    tail
    0.28
    oppers
    0.28
    ridden
    0.27
    lace
    0.26
     articles
    0.26
    Articles
    0.26
     fet
    0.26
    Activations Density 1.646%

    No Known Activations