© 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. 51964
    Prev
    Next
    INDEX
    Explanations

    satisfy conditions and constraints

    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
    Ĺı
    -0.08
     Savo
    -0.07
    ault
    -0.07
    odash
    -0.07
    sert
    -0.07
    ature
    -0.07
    çģ£
    -0.07
    orp
    -0.07
    alité
    -0.07
    olim
    -0.07
    POSITIVE LOGITS
    :
    0.09
    ä¸Ģå®ļçļĦ
    0.08
    å¦Ĥä¸ĭ
    0.08
     tremend
    0.07
    ierz
    0.07
    åīįè¿°
    0.07
    åIJĮæł·çļĦ
    0.07
    gadas
    0.07
    :]
    0.07
    oppen
    0.07
    Activations Density 0.006%

    No Known Activations