© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 30378
    Prev
    Next
    INDEX
    Explanations

    emoticons

    np_acts-logits-general · gemini-2.5-flash-lite

    informal or colloquial language, particularly slang terms and casual expressions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
    å¾Ĺå¿ĥ
    -0.08
    ĥģ
    -0.06
    Lua
    -0.06
    çļĦæīĢæľīä½ľåĵģ
    -0.06
    İĺ
    -0.06
    unsafe
    -0.06
    ently
    -0.06
    å¾ĹæĪij
    -0.06
    åĢºåĪ¸ä¿¡æģ¯
    -0.06
    ÙĦÙħ
    -0.06
    POSITIVE LOGITS
     ;-)
    0.10
     :)
    0.09
     :-)
    0.09
     ;)
    0.09
    äºĭåĦ¿
    0.08
     ðŁĺī
    0.08
    !),
    0.08
    ãģŁãĤĭ
    0.08
    !).
    0.08
    !)
    0.07
    Activations Density 1.564%

    No Known Activations