© 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. 42724
    Prev
    Next
    INDEX
    Explanations

    code logic

    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
    çī¹å°Ķ
    -0.07
    allah
    -0.07
    大éĥ¨åĪĨçļĦ
    -0.07
    å¢ħ
    -0.06
    å¾Ģ常
    -0.06
    æĥķ
    -0.06
    oca
    -0.06
    æ¥
    -0.06
    ogi
    -0.06
    æıīäºĨ
    -0.06
    POSITIVE LOGITS
    æĮīåħ¶
    0.10
    æł¹æį®åħ¶
    0.09
    æī¾åĪ°èĩªå·±
    0.08
    åı¯ä»¥æł¹æį®
    0.08
    _hook
    0.08
    ÙĦØ·
    0.08
     astr
    0.08
    zos
    0.07
    èĩªè¡ĮæıIJä¾Ľ
    0.07
    (number
    0.07
    Activations Density 0.109%

    No Known Activations