© 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. 51926
    Prev
    Next
    INDEX
    Explanations

    listing syntax structures

    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
    é©»åįİ
    -0.08
    лÑĥÑĥ
    -0.06
    èĦĸ
    -0.06
    trico
    -0.06
    PLAN
    -0.06
    -news
    -0.06
    غÙĬ
    -0.06
    kaus
    -0.06
    ÑĢин
    -0.06
    è¶Ł
    -0.06
    POSITIVE LOGITS
    éħį对
    0.09
    ë¹Ī
    0.08
    è·Łèĩªå·±
    0.08
    åıĮè¾¹
    0.08
    åĬŁ
    0.08
     Dup
    0.08
    åĴĮèĩªå·±
    0.08
    å¹³è¡Į
    0.07
     paired
    0.07
     pairing
    0.07
    Activations Density 0.015%

    No Known Activations