© 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. 29164
    Prev
    Next
    INDEX
    Explanations

    be

    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
    人们çļĦ
    -0.30
    ãģĹãģĭãģªãģĦ
    -0.26
    ORY
    -0.25
    çĦĻ
    -0.24
     Yesterday
    -0.24
    ensch
    -0.24
    .defineProperty
    -0.24
    itary
    -0.23
    人åĢij
    -0.23
    asy
    -0.23
    POSITIVE LOGITS
    åĭĭ
    0.30
    <source
    0.26
     stall
    0.26
     trainer
    0.25
    å¢ŀ
    0.25
     officer
    0.25
    èĢģ乡
    0.24
     Officer
    0.24
     ***/↵
    0.23
    æ¦ķ
    0.23
    Activations Density 1.451%

    No Known Activations