© 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. 25-TRANSCODER-HP
    7. 108059
    Prev
    Next
    INDEX
    Explanations

    environments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oria
    -0.28
    dda
    -0.27
    gunta
    -0.26
     histories
    -0.25
    天èĬ±æĿ¿
    -0.25
    DAL
    -0.25
    äºĨè§£æĽ´å¤ļ
    -0.24
    èµĮ
    -0.24
    缴è§Ĥ
    -0.24
    åĽĽå·Ŀçľģ
    -0.24
    POSITIVE LOGITS
     ,č↵
    0.28
    ì¸ł
    0.25
    ÑĢÑĥÑģ
    0.25
    æİĸ
    0.24
    ä¸ĢåŃĹ
    0.24
     =>$
    0.23
    (),č↵
    0.23
    èļ¤
    0.23
    $content
    0.23
     Buffered
    0.23
    Activations Density 0.913%

    No Known Activations