© 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. 58788
    Prev
    Next
    INDEX
    Explanations

    temporary storage or buffer

    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
    alow
    -0.07
    液ä¸Ń
    -0.07
    ello
    -0.07
    lectron
    -0.07
    :border
    -0.06
     воло
    -0.06
    issimo
    -0.06
    çīĩçīĩ
    -0.06
    éļĶ
    -0.06
    æºĸ
    -0.06
    POSITIVE LOGITS
    åŃĺåĤ¨
    0.10
     storing
    0.10
    çĶ¨äºİ
    0.10
     temporary
    0.09
     storage
    0.09
    åŃĺæĶ¾
    0.09
    temporary
    0.09
    Storage
    0.08
     Temporary
    0.08
     cache
    0.08
    Activations Density 0.008%

    No Known Activations