© 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. 851
    Prev
    Next
    INDEX
    Explanations

    code website integration

    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
    arani
    -0.08
    .documentation
    -0.07
    åĹ
    -0.07
    agul
    -0.07
    precated
    -0.06
    å¾·åĪ©
    -0.06
     documentación
    -0.06
    æ³ī
    -0.06
    IOUS
    -0.06
    é¢ľ
    -0.06
    POSITIVE LOGITS
    æ¿Ģæ´»
    0.09
    ä½ľä¸ļæŶ
    0.08
    -filled
    0.08
    actual
    0.08
    -vars
    0.08
     actual
    0.08
    andom
    0.08
    çĦī
    0.07
     Actual
    0.07
     Aktiv
    0.07
    Activations Density 0.443%

    No Known Activations