© 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. 4617
    Prev
    Next
    INDEX
    Explanations

    variable declarations

    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
    ย
    -0.08
    eward
    -0.07
    iju
    -0.07
    itte
    -0.07
    agin
    -0.07
    eny
    -0.07
    inaldo
    -0.07
    åijĺçļĦ
    -0.06
    anga
    -0.06
     franqu
    -0.06
    POSITIVE LOGITS
     [,
    0.09
    htar
    0.07
     result
    0.07
    áŁĭ
    0.07
    zelfde
    0.07
    æĪij们çļĦçĶŁæ´»
    0.06
     reform
    0.06
    orra
    0.06
    -available
    0.06
    ظار
    0.06
    Activations Density 0.076%

    No Known Activations