© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4625
    Prev
    Next
    INDEX
    Explanations

    product rule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    बर
    -0.09
    ÄIJT
    -0.08
    /validation
    -0.08
    egasus
    -0.08
    erland
    -0.08
    éch
    -0.07
    erken
    -0.07
    apur
    -0.07
    çIJ¥
    -0.07
    .datab
    -0.07
    POSITIVE LOGITS
    æĬ«
    0.08
    ç»Ļä»ĸçļĦ
    0.06
    管æīĢ
    0.06
    ä¸ĺ
    0.06
    ä¼¼éĶ¦
    0.06
     formula
    0.06
     scoring
    0.06
    fd
    0.06
    æľ½
    0.06
     denominator
    0.06
    Activations Density 0.003%

    No Known Activations