© 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. 40156
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or symbols

    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
    人çļĦä¸ĢçĶŁ
    -0.06
    urg
    -0.06
    çĶµè¯ĿåĴ¨è¯¢
    -0.06
    statt
    -0.06
    Latch
    -0.06
    çªģåĩºéĹ®é¢ĺ
    -0.06
    人æĿ¥è¯´
    -0.06
    oy
    -0.06
     Born
    -0.05
     mid
    -0.05
    POSITIVE LOGITS
    -bre
    0.08
    valg
    0.08
    áŀ¸
    0.07
    ÙħÙĦÙĩ
    0.07
    кÑģа
    0.07
    engel
    0.07
    illac
    0.07
    omain
    0.07
    iland
    0.07
    åĴ
    0.07
    Activations Density 0.269%

    No Known Activations