© 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. 58923
    Prev
    Next
    INDEX
    Explanations

    pairs and tuples

    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
    åłĤåłĤ
    -0.07
    æ½
    -0.07
    uito
    -0.06
    æĪij们æ¯ı个人
    -0.06
    uit
    -0.06
    uard
    -0.06
    _REFERENCE
    -0.06
    绣é¢Ĩ
    -0.06
    ilian
    -0.06
    ro
    -0.06
    POSITIVE LOGITS
     pairs
    0.08
    COPE
    0.07
    age
    0.07
    _MAKE
    0.07
     tuples
    0.07
    quine
    0.07
    zcze
    0.07
    à¸Ħวัà¸Ļ
    0.07
    pairs
    0.07
    éĺ¿å§Ĩ
    0.07
    Activations Density 0.005%

    No Known Activations