© 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. 42751
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    zia
    -0.28
    mite
    -0.26
    DCF
    -0.26
     frags
    -0.26
    holes
    -0.26
    æ±
    -0.25
    槲
    -0.24
    URES
    -0.24
    WARN
    -0.24
    .decorate
    -0.24
    POSITIVE LOGITS
     further
    0.53
    è¿Ľä¸ĢæŃ¥
    0.43
     clearly
    0.39
     where
    0.39
     just
    0.37
    Con
    0.35
     incident
    0.35
    éĢ²ä¸ĢæŃ¥
    0.34
    Further
    0.34
    con
    0.34
    Activations Density 0.009%

    No Known Activations