© 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. 20854
    Prev
    Next
    INDEX
    Explanations

    historical events and claims

    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
    usher
    -0.08
    ä¸įæĶ¾å¼ĥ
    -0.07
    षà¥į
    -0.07
    Comple
    -0.07
    UserID
    -0.06
    okane
    -0.06
    ä½łæĺ¯æĪijçļĦ
    -0.06
    ìĿ´íĶĦ
    -0.06
    åį´ä¸įèĥ½
    -0.06
    .inline
    -0.06
    POSITIVE LOGITS
     actually
    0.19
    羣å®ŀçļĦ
    0.19
     actual
    0.18
    çļĦå®ŀéĻħ
    0.18
    羣æŃ£çļĦ
    0.17
    å®ŀéĻħ
    0.17
    羣æŃ£
    0.17
    çļĦ羣å®ŀ
    0.17
    actual
    0.17
    å®ŀéĻħçļĦ
    0.17
    Activations Density 0.381%

    No Known Activations