© 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. 51967
    Prev
    Next
    INDEX
    Explanations

    frame of reference

    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
    ابÛĮ
    -0.08
     manh
    -0.07
     kapit
    -0.07
    leven
    -0.07
    нÑıка
    -0.07
    cap
    -0.07
    ÑĪов
    -0.07
    oad
    -0.07
    åĽ½éŨ
    -0.06
    æĬĢæľ¯æĢ§
    -0.06
    POSITIVE LOGITS
     stationary
    0.08
     tilted
    0.07
    quir
    0.07
    ä¸Ń以
    0.07
    otime
    0.07
    é¼
    0.07
    ä¸Ńå¾ĹåĪ°
    0.07
    áĥĶáĥĹ
    0.07
    å¦į
    0.07
    antics
    0.06
    Activations Density 0.003%

    No Known Activations