© 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. 55591
    Prev
    Next
    INDEX
    Explanations

    categorized into groups

    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
    æģIJæĢķ
    -0.07
    izzie
    -0.07
    aso
    -0.07
    наÑĤ
    -0.07
    æģIJ
    -0.07
    ĭ
    -0.06
    izio
    -0.06
    κει
    -0.06
    çŃīçĸ¾çĹħ
    -0.06
    èķĬ
    -0.06
    POSITIVE LOGITS
     ÑģобÑģÑĤвенно
    0.12
    两大类
    0.09
    éĥ¨åĪĨç»ĦæĪIJ
    0.08
    ä¸Ģç§įæĺ¯
    0.08
    çĦ¶åIJİæĺ¯
    0.08
     olmak
    0.08
    ãĤĤãģ®ãģ¨
    0.07
     vs
    0.07
    ä¹ĭåĪĨ
    0.07
    è¿ĺæľīå°±æĺ¯
    0.07
    Activations Density 0.502%

    No Known Activations