© 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. 19426
    Prev
    Next
    INDEX
    Explanations

    on

    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
    æĵ¦
    -0.31
    ubit
    -0.28
    åĮħ
    -0.27
    ç»ijå®ļ
    -0.26
    EEK
    -0.26
    elry
    -0.26
    æĬ¬èµ·
    -0.26
    rist
    -0.26
    vit
    -0.25
    ploy
    -0.25
    POSITIVE LOGITS
    ä¼Ļä¼´
    0.29
    Ñģон
    0.27
    å®ī稳
    0.25
    PP
    0.24
     Tata
    0.24
    ä¸ĢéĿ¢
    0.24
    nf
    0.24
    partners
    0.24
    <Project
    0.24
    _LANGUAGE
    0.23
    Activations Density 0.012%

    No Known Activations