© 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. 18841
    Prev
    Next
    INDEX
    Explanations

    Reader

    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
     project
    -0.33
    è¯¥é¡¹çĽ®
    -0.31
    代åĬŀ
    -0.29
     Stam
    -0.29
    é¡¹çĽ®
    -0.29
     agents
    -0.28
    éĬ®
    -0.28
    project
    -0.27
    代çIJĨ
    -0.27
     exec
    -0.27
    POSITIVE LOGITS
    ublisher
    0.30
    ç³»ç»ŁçļĦ
    0.29
    对åѦçĶŁ
    0.28
    ÑģиÑģÑĤем
    0.27
    æ¢Ĩ
    0.26
    è¿Ľè¡Įåħ¨éĿ¢
    0.26
    Publisher
    0.25
    sku
    0.25
    cole
    0.24
    иÑģÑĤем
    0.24
    Activations Density 1.042%

    No Known Activations