© 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. 30444
    Prev
    Next
    INDEX
    Explanations

    code/reports

    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
    individual
    -0.28
    ä¸Ģéģį
    -0.26
    antas
    -0.26
     individual
    -0.26
    ä¸Ģè¡Į
    -0.25
    è¡Ģ液循çݯ
    -0.25
     fadeIn
    -0.24
    åĻ»
    -0.24
    -device
    -0.24
    çĸ¯
    -0.24
    POSITIVE LOGITS
    ysis
    0.30
    椿
    0.28
     blur
    0.26
     Chick
    0.25
    æĤ¨çļĦåŃ©åŃIJ
    0.24
    avors
    0.24
    ä¼łç»Ł
    0.24
    åĪ¹
    0.24
    angers
    0.24
    kick
    0.24
    Activations Density 1.902%

    No Known Activations