© 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. 142679
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Negative Logits
    ationToken
    -0.35
    éĹ®è¯¢
    -0.27
    NSURL
    -0.26
    çŀŃ
    -0.26
     Avec
    -0.25
    hyp
    -0.25
    岸
    -0.25
    utow
    -0.25
     hyp
    -0.25
    趸
    -0.24
    POSITIVE LOGITS
    éĻµ
    0.28
    æĪĺèĥľ
    0.26
    åħĭæľį
    0.26
    tractor
    0.26
    çļĦ女åŃ©
    0.26
    -place
    0.25
    fram
    0.24
    .rs
    0.24
    gel
    0.24
    endum
    0.23
    Activations Density 14.133%

    No Known Activations