© 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. 24263
    Prev
    Next
    INDEX
    Explanations

    smith

    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
    boards
    -0.28
     bub
    -0.26
    æ±īè¯Ń
    -0.25
     ngu
    -0.25
     autistic
    -0.24
    дов
    -0.24
    _candidate
    -0.23
    cola
    -0.23
     raw
    -0.23
     uncomfort
    -0.23
    POSITIVE LOGITS
    ä¸ĭ乡
    0.28
    容
    0.27
    -cons
    0.27
    ROTO
    0.27
    +(\
    0.26
     tallest
    0.26
    åĪ°è´¦
    0.26
     wid
    0.26
     invo
    0.25
    /tool
    0.25
    Activations Density 0.014%

    No Known Activations