© 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. 22178
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    好å¤Ħ
    -0.30
    å½ĵåľ°
    -0.27
     counties
    -0.26
    è£½ä½ľ
    -0.26
    gh
    -0.25
     sublicense
    -0.25
    ineTransform
    -0.24
    inci
    -0.24
    <location
    -0.24
    Monad
    -0.24
    POSITIVE LOGITS
     scalar
    0.26
     scal
    0.26
     dés
    0.25
    otle
    0.25
    ÙĩÙĨ
    0.24
    rito
    0.24
    奢
    0.24
     Arrival
    0.24
    æĸ¯é¡¿
    0.24
     imp
    0.24
    Activations Density 0.006%

    No Known Activations