© 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. 4282
    Prev
    Next
    INDEX
    Explanations

    annular shapes and rings

    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
    íĮħ
    -0.07
    ãģ¾ãģ¾
    -0.07
    org
    -0.07
    ÙĪÙĨس
    -0.06
    бÑĢ
    -0.06
    upt
    -0.06
    olti
    -0.06
    ç³»ç»ŁéĽĨæĪIJ
    -0.06
    ä½ĵç³»
    -0.06
    äºĨä¸ĢåįĬ
    -0.06
    POSITIVE LOGITS
    -shaped
    0.11
    åľ°å¸¦
    0.09
    ette
    0.09
    çĬ¶çļĦ
    0.08
    çĬ¶
    0.08
    -like
    0.08
    -separated
    0.08
    ar
    0.08
     hẹp
    0.08
    宽度
    0.07
    Activations Density 0.011%

    No Known Activations