© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 18041
    Prev
    Next
    INDEX
    Explanations

    Code and licensing information

    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
     online
    -0.24
    åľ¨çº¿
    -0.24
    ialect
    -0.24
    ä¸ĢæľŁ
    -0.24
    faculty
    -0.23
    ë²
    -0.23
    à¹Ģà¸Ł
    -0.23
    éĢĤ度
    -0.23
     Online
    -0.23
    SUMER
    -0.23
    POSITIVE LOGITS
    inea
    0.29
    qv
    0.27
    qs
    0.27
     Beh
    0.26
    stell
    0.25
    psc
    0.25
    q
    0.25
    qx
    0.25
    ä½ľ
    0.25
    еÑģÑĤв
    0.25
    Activations Density 0.003%

    No Known Activations