© 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. 97941
    Prev
    Next
    INDEX
    Explanations

    so

    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
    è¿ĩçļĦ
    -0.26
     factors
    -0.26
    over
    -0.26
    çļĦåĽłç´ł
    -0.26
    è¿ĺæľīä¸ĢäºĽ
    -0.25
    صÙĦا
    -0.24
    Ä©nh
    -0.24
    ocz
    -0.24
     aids
    -0.24
    è¿ĺéľĢ
    -0.23
    POSITIVE LOGITS
    rompt
    0.32
    ä¸įåĪĨ
    0.31
    ç»Ĭ
    0.27
    icity
    0.26
    第ä¸ĢæŶéĹ´
    0.25
    次
    0.25
     morphology
    0.24
    åľ¨åħ¶
    0.24
    æľīä»·åĢ¼çļĦ
    0.24
     condem
    0.23
    Activations Density 0.008%

    No Known Activations