© 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. 33390
    Prev
    Next
    INDEX
    Explanations

    low, small, relative, rare

    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
    ä½Ĩä¸įè¦ģ
    -0.09
    éªĭ
    -0.08
     Zub
    -0.08
    æľĢéļ¾
    -0.08
    osphate
    -0.07
    éļ¾
    -0.07
    urement
    -0.07
    .ready
    -0.07
    slick
    -0.07
     Caz
    -0.07
    POSITIVE LOGITS
     ÙĨسب
    0.11
     ÙĨس
    0.10
     compared
    0.09
     relative
    0.09
    -ish
    0.08
    relative
    0.08
     comparatively
    0.08
    çĽ¸å¯¹èĢĮè¨Ģ
    0.08
    åį´èĥ½
    0.07
     relatively
    0.07
    Activations Density 0.244%

    No Known Activations