© 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. 22195
    Prev
    Next
    INDEX
    Explanations

    Email snippets

    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
    çĻ»
    -0.29
    èĢĮä¸Ķ
    -0.27
     doÄŁ
    -0.27
    å¢Ļ
    -0.26
    åĺī宾
    -0.26
    éĺ³
    -0.25
    翼
    -0.25
     daģı
    -0.25
    igator
    -0.25
    avi
    -0.24
    POSITIVE LOGITS
     trolls
    0.27
     equivalents
    0.27
    ãģĮãģ§ãģįãĤĭ
    0.26
     çalÄ±ÅŁma
    0.25
    arguments
    0.25
    iguiente
    0.24
    iosa
    0.24
     compositions
    0.24
    _();↵
    0.24
    gráfica
    0.24
    Activations Density 0.065%

    No Known Activations