© 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. 52220
    Prev
    Next
    INDEX
    Explanations

    quantitative concepts

    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
    éĢģæĿ¥
    -0.07
    olja
    -0.07
    åķ¸
    -0.07
    vail
    -0.07
    ฯ
    -0.07
    olata
    -0.07
    edis
    -0.07
    åĽłä¸ºè¿Ļ个
    -0.07
    FieldValue
    -0.07
    ael
    -0.07
    POSITIVE LOGITS
    ä½ıäºĨ
    0.08
    iers
    0.08
     extracted
    0.08
    åħ¥åº§
    0.07
    èĩªåĬ¨
    0.07
     automatically
    0.07
    ä¸ĢéĶ®
    0.07
    åı¯ä»¥å¸®åĬ©æĪij们
    0.07
    based
    0.07
    åı¯çĶ¨äºİ
    0.07
    Activations Density 0.047%

    No Known Activations