© 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. 37700
    Prev
    Next
    INDEX
    Explanations

    separate, distinct, independent

    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
    éĤ£äºĽ
    -0.08
    äºĽ
    -0.07
    èħ¹åľ°
    -0.07
    ANDA
    -0.07
    åĵij
    -0.07
    chos
    -0.07
    çīĪæĿĥæīĢæľī
    -0.07
    _examples
    -0.07
     Beispiele
    -0.07
    ouse
    -0.07
    POSITIVE LOGITS
     separate
    0.14
    åįķçĭ¬çļĦ
    0.14
    åįķçĭ¬
    0.13
     separately
    0.12
    çĭ¬ç«ĭçļĦ
    0.12
     distinct
    0.12
     Separate
    0.11
     seperate
    0.10
    çĭ¬ç«ĭ
    0.10
     ë³ĦëıĦìĿĺ
    0.10
    Activations Density 0.051%

    No Known Activations