© 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. 30315
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    Negative Logits
    [];č↵
    -0.28
    iese
    -0.25
    .gridView
    -0.25
     remotely
    -0.25
    .Enter
    -0.25
    ä¹Łå¸ĮæľĽ
    -0.24
     Tre
    -0.24
    .opend
    -0.24
     shaken
    -0.24
    ieri
    -0.24
    POSITIVE LOGITS
    èĹı
    0.32
    TCHA
    0.27
    .classes
    0.26
    åIJĪä¸Ģ
    0.26
    away
    0.26
    ì¼Ģ
    0.26
    ä¸Ģ带
    0.26
    cul
    0.25
    ç»ĻæĪij们
    0.25
    ç²¹
    0.25
    Activations Density 1.316%

    No Known Activations