© 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. 12-TRANSCODER-HP
    7. 22092
    Prev
    Next
    INDEX
    Explanations

    Vers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    rud
    -0.27
    å¢ŀéĩı
    -0.26
     presidents
    -0.25
     Geli
    -0.25
    ERICA
    -0.25
    éĩįå¿ĥ
    -0.24
    éĢĴ
    -0.24
    å®ŀè·µ
    -0.24
    æł·
    -0.23
    ayment
    -0.23
    POSITIVE LOGITS
     enforce
    0.26
     enforcing
    0.25
     Pocket
    0.25
    ä¿®å¤į
    0.25
     impose
    0.24
    åģļä¸įåĪ°
    0.24
    æĸĩåĮĸ建设
    0.24
    CP
    0.24
    ounder
    0.24
    æ
    0.24
    Activations Density 0.154%

    No Known Activations