© 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. 112904
    Prev
    Next
    INDEX
    Explanations

    technical/academic writing

    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
    emain
    -0.31
    ips
    -0.30
    顺
    -0.27
    款车åŀĭ
    -0.27
    azers
    -0.27
     ë¶ģ
    -0.26
    æŃ£
    -0.25
    usable
    -0.25
    endir
    -0.25
    ÙĨع
    -0.25
    POSITIVE LOGITS
    çļĦæĹ¥åŃIJ
    0.27
    goo
    0.25
    gie
    0.25
    ç©°
    0.25
    æĬ¥ä»ĩ
    0.24
     beforehand
    0.24
     traumat
    0.24
     adaptive
    0.24
     adaptation
    0.23
    bek
    0.23
    Activations Density 0.003%

    No Known Activations