© 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. 86794
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    åŁŁ
    -0.26
    ')),↵
    -0.24
    >>,↵
    -0.23
    eur
    -0.23
    ecessarily
    -0.23
    blast
    -0.23
    ä¸įæ¸ħ
    -0.23
    upo
    -0.23
    èij¡
    -0.23
    _sz
    -0.23
    POSITIVE LOGITS
    éªIJ
    0.26
    çĤ¯
    0.25
    hoff
    0.24
    ä¹Łæľīä¸ĢäºĽ
    0.23
     competency
    0.23
    AXB
    0.23
     xd
    0.23
     prescribe
    0.23
    Analyzer
    0.23
    åħīæĺİ
    0.23
    Activations Density 0.297%

    No Known Activations