© 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. 22-TRANSCODER-HP
    7. 98018
    Prev
    Next
    INDEX
    Explanations

    Dal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¼
    -0.31
    idon
    -0.28
    æ·ĭ
    -0.28
    å¾Ī好
    -0.27
    åį´è¢«
    -0.26
    fos
    -0.25
    ä»İä¸Ń
    -0.25
    åħij
    -0.25
    burn
    -0.25
    xDF
    -0.24
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.36
    ä¸įåIJĮç±»åŀĭ
    0.36
     different
    0.36
    çļĦä¸įåIJĮ
    0.35
    different
    0.33
    ä¸įåIJĮ
    0.32
    ifferent
    0.29
    æľīæīĢä¸įåIJĮ
    0.29
     diferente
    0.28
     verschiedenen
    0.28
    Activations Density 0.002%

    No Known Activations