© 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. 62825
    Prev
    Next
    INDEX
    Explanations

    biological process or activity

    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
    们çļĦ
    -0.10
    们
    -0.10
    åĢij
    -0.09
    ä»¬åľ¨
    -0.09
    ów
    -0.09
    (s
    -0.08
    们éĥ½
    -0.08
    ëĵ¤ìĿ´
    -0.08
     ihres
    -0.08
    sand
    -0.08
    POSITIVE LOGITS
    -lite
    0.09
    osis
    0.07
    macros
    0.07
     Raya
    0.07
    bows
    0.07
    undry
    0.07
    /the
    0.06
    Defined
    0.06
     practiced
    0.06
     occurring
    0.06
    Activations Density 0.531%

    No Known Activations