© 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. 49318
    Prev
    Next
    INDEX
    Explanations

    data following

    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
    ehl
    -0.08
    edList
    -0.08
    enner
    -0.07
    ¹
    -0.07
    çĤľ
    -0.07
    klang
    -0.07
    ingly
    -0.07
    kasten
    -0.07
    é»Ħè±Ĩ
    -0.06
    太éĥİ
    -0.06
    POSITIVE LOGITS
    enance
    0.09
    modo
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    ئة
    0.08
    ä¸ļåĬ¡çŁ¥è¯Ĩ
    0.07
    wan
    0.07
    éļĽ
    0.07
     Caught
    0.07
    igned
    0.07
    ç»ĻæĪijçķĻè¨Ģ
    0.07
    Activations Density 0.079%

    No Known Activations