© 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. 41277
    Prev
    Next
    INDEX
    Explanations

    Code/URLs/function names

    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
    kal
    -0.28
    -rule
    -0.27
    <Element
    -0.27
    (LogLevel
    -0.26
     ruled
    -0.26
    SEL
    -0.26
    pez
    -0.26
     Boots
    -0.25
    .Iterator
    -0.25
    anse
    -0.25
    POSITIVE LOGITS
    ä¿¡æģ¯åıijå¸ĥ
    0.27
     bearing
    0.26
     Wrong
    0.25
    éĿ¢åŃIJ
    0.25
    mour
    0.25
     Affairs
    0.25
    CJK
    0.24
    æ¦ľ
    0.24
     wound
    0.24
    对æłĩ
    0.24
    Activations Density 0.002%

    No Known Activations