© 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. 20-TRANSCODER-HP
    7. 64504
    Prev
    Next
    INDEX
    Explanations

    Zero, false, null values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ä±ÅŁÄ±
    -0.27
    _ABORT
    -0.25
    arket
    -0.25
    åħĭæľį
    -0.25
    permalink
    -0.24
    åģı
    -0.24
    åĬŀæ³ķ
    -0.23
    ç§ĺ
    -0.23
    udad
    -0.23
    templ
    -0.23
    POSITIVE LOGITS
    SW
    0.28
    æµ·æ£ł
    0.26
     jung
    0.26
    çľĭäºĨä¸Ģ
    0.25
    Reach
    0.25
    ording
    0.25
    è¿Ļç±»
    0.25
    stype
    0.25
    SCAN
    0.25
    _eg
    0.25
    Activations Density 10.644%

    No Known Activations