© 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. 42769
    Prev
    Next
    INDEX
    Explanations

    Non-English

    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
    天æ°Ķ
    -0.29
    çºłéĶĻ
    -0.28
    ulators
    -0.27
     ne
    -0.27
    ellar
    -0.26
     Bears
    -0.25
     neutral
    -0.25
     scraped
    -0.25
     Pel
    -0.25
     weather
    -0.24
    POSITIVE LOGITS
    ÑĢаÑģÑĤ
    0.32
    èļ±
    0.26
    isman
    0.26
    åĬ¨æĦŁ
    0.26
    ä¼Ĭæĸ¯
    0.26
    ym
    0.26
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.25
    hou
    0.25
    缦
    0.25
    æīĢåľ¨åľ°
    0.25
    Activations Density 0.001%

    No Known Activations