© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 55695
    Prev
    Next
    INDEX
    Explanations

    technical/code constructs

    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
    ello
    -0.07
    åķĨ
    -0.06
    ful
    -0.06
    æľīéĻIJçļĦ
    -0.06
    weise
    -0.06
    ä¸įçķı
    -0.06
    á»ijng
    -0.06
    wares
    -0.06
    ingers
    -0.06
    amentos
    -0.06
    POSITIVE LOGITS
    ields
    0.08
    estroy
    0.08
    çİīå±±
    0.08
    纯æ£ī
    0.08
     '::
    0.08
    å±¹
    0.07
    STATIC
    0.07
     EITHER
    0.07
    æĸĵ
    0.07
    ç§ijæĬĢåѦéĻ¢
    0.07
    Activations Density 0.012%

    No Known Activations