© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62945
    Prev
    Next
    INDEX
    Explanations

    braconidae, cribriform, sigourney, lemont, tuberculin, lacrosse, tracheostomy, geriatric, mesenteric, surgical

    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
    ONES
    -0.07
    ALLY
    -0.07
    ITY
    -0.07
    NESS
    -0.07
    Âł
    -0.06
    USED
    -0.06
    ENTA
    -0.06
    estination
    -0.06
    ationen
    -0.06
     ones
    -0.06
    POSITIVE LOGITS
    ier
    0.11
    çıij
    0.09
    %C
    0.09
    羣æĬĵ
    0.09
    iern
    0.09
    æł·åŃIJ
    0.08
    il
    0.08
    å°½èĩªå·±
    0.08
    ut
    0.08
    erer
    0.08
    Activations Density 0.530%

    No Known Activations