© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56522
    Prev
    Next
    INDEX
    Explanations

    '%', `pow`, `String`, `1`, `0`

    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
    impi
    -0.08
    ROTO
    -0.08
    uš
    -0.08
    ÏīÏĤ
    -0.07
    åIJİæĦŁ
    -0.07
    aign
    -0.07
    åįļ士çłĶ究çĶŁ
    -0.07
    åıªèĥ½çĶ¨
    -0.07
    upal
    -0.07
    ä¸į妥
    -0.07
    POSITIVE LOGITS
    é»ĺ
    0.07
    å¥ĩ迹
    0.07
    å½¢å¼ı
    0.07
    åīįæĸ¹çļĦ
    0.06
    èĵī
    0.06
    éļ±
    0.06
    ÏĦί
    0.06
    PrototypeOf
    0.06
    indel
    0.06
    éļIJ
    0.06
    Activations Density 0.080%

    No Known Activations