© 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. 129110
    Prev
    Next
    INDEX
    Explanations

    negation

    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
     Zag
    -0.28
    ahl
    -0.28
    arty
    -0.26
     Josef
    -0.26
    PHY
    -0.26
    emic
    -0.25
    ç¾²
    -0.25
    çļĦæĦıæĢĿ
    -0.24
     bÃłn
    -0.24
    jab
    -0.24
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    1.09
    ä¹Łæĺ¯å¦ĤæѤ
    0.75
    åIJĮæł·
    0.41
     similarly
    0.39
     likewise
    0.38
     Likewise
    0.36
    ä¹ŁåIJĮæł·
    0.36
     Similarly
    0.35
    ä¸Ģæł·
    0.35
    ä¾ĭå¤ĸ
    0.35
    Activations Density 0.008%

    No Known Activations