© 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. 29473
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ä¼ģä¸ļæıIJä¾Ľ
    -0.29
     screened
    -0.26
    patches
    -0.25
    (Screen
    -0.24
    owed
    -0.24
    pike
    -0.23
     Accent
    -0.23
     shaded
    -0.23
     Bol
    -0.23
     bowling
    -0.23
    POSITIVE LOGITS
    çļĦéģĵçIJĨ
    0.26
    ire
    0.26
    egan
    0.26
    çļĦçŁ¥è¯Ĩ
    0.25
    åĵī
    0.25
    loit
    0.24
     started
    0.24
    eger
    0.24
     arter
    0.24
    çļĦåIJĮæŶ
    0.24
    Activations Density 1.013%

    No Known Activations