© 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. 22-TRANSCODER-HP
    7. 86869
    Prev
    Next
    INDEX
    Explanations

    technical jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    [attr
    -0.27
    ewish
    -0.26
     Fol
    -0.26
    åĵŃæ³£
    -0.25
    åıįè¿ĩæĿ¥
    -0.25
     Churches
    -0.24
    æ¯ıä¸Ģ
    -0.24
    emons
    -0.24
    æľĿå»·
    -0.24
     Around
    -0.24
    POSITIVE LOGITS
    iversal
    0.26
    valuate
    0.25
    `s
    0.24
     adap
    0.24
    次
    0.24
     darn
    0.24
     cans
    0.24
    pery
    0.23
    iosis
    0.23
    åľ
    0.23
    Activations Density 0.023%

    No Known Activations