© 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. 44003
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
    nock
    -0.09
    ä¸ĩéĩĮ
    -0.08
    éª
    -0.07
    acca
    -0.07
    ITHER
    -0.07
     lust
    -0.07
    tsy
    -0.07
    è¯Ħæ¯Ķ
    -0.07
    elry
    -0.07
    лдÑĭ
    -0.07
    POSITIVE LOGITS
    èĢĮèĩªå·±
    0.08
    اÙĦÙģ
    0.07
    isle
    0.07
    并æıIJ交
    0.06
    ç²
    0.06
    ķĮ
    0.06
    ç¨į
    0.06
    oby
    0.06
    çĦ¶åIJİå°±
    0.06
    è¦ģ害
    0.06
    Activations Density 0.093%

    No Known Activations