© 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. 10893
    Prev
    Next
    INDEX
    Explanations

    section markers

    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
    pedia
    -0.06
    onus
    -0.06
    Really
    -0.06
    ä¸įä»ħä»ħ
    -0.06
    éĢ¢
    -0.06
    _rpc
    -0.06
    çĶ¨åĪ°
    -0.06
    ä¸įä»ħä»ħæĺ¯
    -0.06
    afe
    -0.06
    +
    -0.06
    POSITIVE LOGITS
     prelimin
    0.10
    çļĦåŁºæľ¬æĥħåĨµ
    0.09
    ãģ¯ãģĺãĤģ
    0.09
    èµ·æīĭ
    0.09
     basics
    0.09
     Basics
    0.09
     overview
    0.09
    ãģ¾ãģļ
    0.09
    绪
    0.08
    æ¦ĤåĨµ
    0.08
    Activations Density 0.085%

    No Known Activations