© 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. 29319
    Prev
    Next
    INDEX
    Explanations

    Sentences starting with "As"

    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
     comm
    -0.31
    å½±
    -0.27
     com
    -0.27
     apl
    -0.26
     putt
    -0.26
    ekt
    -0.26
    Ĥ¨
    -0.25
     shall
    -0.25
     continually
    -0.24
    &t
    -0.24
    POSITIVE LOGITS
    ç´ł
    0.26
    å§Ķå±Ī
    0.26
     Coach
    0.25
    decorators
    0.25
    æĭĴ
    0.24
     deny
    0.24
    éļĶ
    0.24
     dạ
    0.24
    ruits
    0.24
    год
    0.23
    Activations Density 3.830%

    No Known Activations