© 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. 59034
    Prev
    Next
    INDEX
    Explanations

    professional medical or writers

    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
    Negative Logits
    abouts
    -0.08
    ÚĨÛĮ
    -0.08
    wards
    -0.08
    aine
    -0.08
    ianas
    -0.07
    forth
    -0.07
    ÑģÑĤÑĢе
    -0.07
    glieder
    -0.07
    åħ¨éĿ¢å»ºè®¾
    -0.07
    apon
    -0.07
    POSITIVE LOGITS
    issimo
    0.10
    ized
    0.09
    ität
    0.09
    -grade
    0.09
    stown
    0.08
    ize
    0.08
    åħ¶äºĭ
    0.08
    ization
    0.08
    -looking
    0.08
    izes
    0.08
    Activations Density 0.038%

    No Known Activations