© 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. 30-TRANSCODER-HP
    7. 95285
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aket
    -0.28
    ério
    -0.28
    thesize
    -0.27
    yms
    -0.26
    åľ»
    -0.25
    åѦåĪ°
    -0.25
     Gathering
    -0.25
    éĴ»
    -0.25
    ardo
    -0.25
     thermal
    -0.25
    POSITIVE LOGITS
    ç¿Į
    0.26
    èĭ±æł¼
    0.26
    ess
    0.25
    çļĦåĪ°æĿ¥
    0.24
    æŀģ
    0.23
     concluded
    0.23
    缸éĢļ
    0.23
    æĺ¯åIJ¦æľī
    0.23
     bạc
    0.23
     jur
    0.23
    Activations Density 0.884%

    No Known Activations

    This feature has no known activations.