© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109521
    Prev
    Next
    INDEX
    Explanations

    or

    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
    Negative Logits
    èĥĨ
    -0.34
     footprint
    -0.28
    èĨ½
    -0.28
    èĥĮ
    -0.27
    essential
    -0.27
    ä¹ĭåŁİ
    -0.26
    ä¸įåı¯æĪĸ缺
    -0.26
    äºĴè¡¥
    -0.24
    ëķħ
    -0.23
    isible
    -0.23
    POSITIVE LOGITS
     preview
    0.27
    ARC
    0.26
    æĸĭ
    0.26
     disqualified
    0.25
    .travel
    0.25
    èĩªèIJ¥
    0.24
    èĮĦ
    0.24
     cruising
    0.24
     sporting
    0.24
    orer
    0.23
    Activations Density 0.175%

    No Known Activations