© 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. 9-TRANSCODER-HP
    7. 29478
    Prev
    Next
    INDEX
    Explanations

    layout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     layouts
    -0.33
     layout
    -0.30
     laying
    -0.28
    -layout
    -0.28
     lay
    -0.27
    inge
    -0.27
     Layout
    -0.26
     Largest
    -0.26
    éĩįå¤į
    -0.26
    åĬ³
    -0.24
    POSITIVE LOGITS
    æłĪ
    0.27
    æĹ¢æľī
    0.27
    åıįæĢĿ
    0.26
    ноÑģÑĤ
    0.26
     theat
    0.25
     Skype
    0.24
     midd
    0.24
    ä¿®çIJĨ
    0.24
    ibil
    0.24
    å½¹
    0.24
    Activations Density 0.473%

    No Known Activations