© 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. 19114
    Prev
    Next
    INDEX
    Explanations

    People being honored/Religion

    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
    ä¸į解
    -0.30
    archy
    -0.30
    ä¹ŀ
    -0.29
    bol
    -0.28
     bol
    -0.27
    ucc
    -0.27
     QVariant
    -0.26
    -strong
    -0.26
     "%.
    -0.26
     xy
    -0.25
    POSITIVE LOGITS
    éĢģåĪ°
    0.28
     sent
    0.27
    fig
    0.27
    Sent
    0.27
    dn
    0.26
     Sent
    0.26
    anded
    0.26
     causa
    0.25
    riz
    0.25
    ç´ĭ
    0.25
    Activations Density 0.234%

    No Known Activations