© 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. 22069
    Prev
    Next
    INDEX
    Explanations

    possessive

    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
     constituted
    -0.29
    ç»Ī身
    -0.26
    egan
    -0.25
    ĮĢ
    -0.24
    ç«Ł
    -0.24
    æīģ
    -0.24
    ifen
    -0.24
    LError
    -0.24
     confidently
    -0.23
     conquer
    -0.23
    POSITIVE LOGITS
    è¿Ļä¸įæĺ¯
    0.26
     duplicates
    0.26
    临
    0.25
    uru
    0.25
    .YesNo
    0.24
     polar
    0.24
    çıł
    0.24
    æĭĻ
    0.24
    /response
    0.24
     Shapiro
    0.24
    Activations Density 0.002%

    No Known Activations