© 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. 4732
    Prev
    Next
    INDEX
    Explanations

    quoted numbers and punctuation

    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
    çŁ
    -0.08
    ushman
    -0.08
    IONE
    -0.07
    Knight
    -0.07
    _BOARD
    -0.07
    ANTS
    -0.07
    ukka
    -0.07
    æīijéĿ¢
    -0.07
    è£
    -0.07
    æĺ¯å®ŀçİ°
    -0.06
    POSITIVE LOGITS
    æ··
    0.08
    æ··åIJĪ
    0.07
    mixed
    0.07
     mixed
    0.07
    åĭĥ
    0.07
    éĤ£ä¹Īåľ¨
    0.06
    ime
    0.06
    åħ·ä½ĵéĹ®é¢ĺ
    0.06
    é¢ĵ
    0.06
    ä¸ŃæŃ¢
    0.06
    Activations Density 0.262%

    No Known Activations