© 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. 99196
    Prev
    Next
    INDEX
    Explanations

    Initials/Abbreviations

    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
    æĸ¯åŁº
    -0.28
    xic
    -0.27
    ivable
    -0.27
     Som
    -0.26
     Tradition
    -0.26
     Exhibition
    -0.26
    çĮª
    -0.25
     piv
    -0.25
    åħ¸
    -0.25
     Trad
    -0.24
    POSITIVE LOGITS
    elman
    0.28
    RTL
    0.25
    operand
    0.25
     cgi
    0.25
    _attrib
    0.25
    tridge
    0.24
     summarize
    0.24
    LEY
    0.24
    hape
    0.24
    edly
    0.24
    Activations Density 0.009%

    No Known Activations