© 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. 32-TRANSCODER-HP
    7. 43133
    Prev
    Next
    INDEX
    Explanations

    bio

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķ¢
    -0.27
    人次
    -0.27
     Montgomery
    -0.25
     isNaN
    -0.25
     cha
    -0.25
    æĭĵ
    -0.25
    à¸ĩ
    -0.24
    è´¢
    -0.24
    CARD
    -0.24
     rew
    -0.24
    POSITIVE LOGITS
    roduction
    0.28
    itted
    0.26
    HTML
    0.26
    èħ¹
    0.25
    uss
    0.25
    liable
    0.25
    è¡¥
    0.25
    privileged
    0.25
    ob
    0.25
    ologically
    0.24
    Activations Density 0.007%

    No Known Activations