© 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. 32-TRANSCODER-HP
    7. 41168
    Prev
    Next
    INDEX
    Explanations

    most

    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
    ENCY
    -0.26
    lan
    -0.26
    .Handler
    -0.26
    -La
    -0.26
     Density
    -0.26
    á½²
    -0.26
     Kelly
    -0.25
    躺
    -0.25
    .LayoutParams
    -0.25
     Levine
    -0.25
    POSITIVE LOGITS
     coat
    0.28
    боÑĢ
    0.27
    åIJĮè¡Į
    0.27
    izi
    0.26
    ç½Ĺæĸ¯
    0.26
    orris
    0.25
    à¹Ģà¸ķ
    0.25
    stakes
    0.25
    æ½¼
    0.25
     zap
    0.25
    Activations Density 0.000%

    No Known Activations