© 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
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21711
    Prev
    Next
    INDEX
    Explanations

    More

    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
    mess
    -0.08
    AMA
    -0.08
    é»ijè±Ĩ
    -0.07
    ama
    -0.07
    çĤĴ
    -0.07
     Mess
    -0.07
    colari
    -0.07
    νÏīν
    -0.07
    çĻ½äºĨ
    -0.07
    RG
    -0.07
    POSITIVE LOGITS
    NotAllowed
    0.07
    oghi
    0.07
    ä¸Ģæİ¢
    0.07
    æľ¬æĸĩå°Ĩä»İ
    0.07
    ota
    0.06
    ãģ»
    0.06
    δε
    0.06
    æľįåĬ¡çļĦ
    0.06
    æľ¬ä½ĵ
    0.06
    æ¡ĤåĨł
    0.06
    Activations Density 0.368%

    No Known Activations