© 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. 96151
    Prev
    Next
    INDEX
    Explanations

    configuration

    np_max-act-logits · gemini-2.0-flash
    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
    -device
    -0.32
    é«ĺéĢŁ
    -0.30
    åŁĭ
    -0.29
    ç½®äºİ
    -0.28
    holm
    -0.28
    aved
    -0.28
    èIJ½åľ¨
    -0.27
    ä¸ĩ个
    -0.27
     devices
    -0.27
     device
    -0.27
    POSITIVE LOGITS
    end
    0.31
    configuration
    0.27
    æķĻ
    0.26
     configuration
    0.26
    inos
    0.26
    纵åIJij
    0.26
    zia
    0.26
     configurations
    0.25
     end
    0.25
    Configuration
    0.25
    Activations Density 0.106%

    No Known Activations