© 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. 4872
    Prev
    Next
    INDEX
    Explanations

    try/except blocks

    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
    Negative Logits
    ints
    -0.06
    uju
    -0.06
    /operator
    -0.06
    statt
    -0.06
    è£ľ
    -0.06
    KP
    -0.06
    OK
    -0.06
    KM
    -0.06
    /comments
    -0.06
    oku
    -0.06
    POSITIVE LOGITS
    èĩªæ£Ģ
    0.08
    anita
    0.08
    μη
    0.08
    èĩªçľģ
    0.08
     self
    0.07
    å±Ĭåħ¨åĽ½
    0.07
    æĪijçļĦä¸ĸçķĮ
    0.07
    åŃ°
    0.07
    çķ´
    0.07
    _readable
    0.07
    Activations Density 0.017%

    No Known Activations