© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21362
    Prev
    Next
    INDEX
    Explanations

    interstitial vacancies

    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
    ittal
    -0.08
    pen
    -0.07
     sequ
    -0.07
    okus
    -0.07
    æĬĬå·¥ä½ľ
    -0.07
    apia
    -0.06
    okr
    -0.06
    ended
    -0.06
    é¼İ
    -0.06
    æĭ¼æİ¥
    -0.06
    POSITIVE LOGITS
    ample
    0.09
    ä¸įæķ¢
    0.08
    空éļĻ
    0.08
     vacancies
    0.07
    çݲçıij
    0.07
    Ø´ÛĮ
    0.07
    衬
    0.07
     vacant
    0.07
     vacancy
    0.07
    eways
    0.07
    Activations Density 0.001%

    No Known Activations