© 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. 31875
    Prev
    Next
    INDEX
    Explanations

    We find results

    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
    ourcem
    -0.07
    é¦ĸåħĪéľĢè¦ģ
    -0.07
    æľĢåĪĿ
    -0.07
    awal
    -0.06
     presup
    -0.06
    è¦ģçŁ¥éģĵ
    -0.06
    ï¼Ī
    -0.06
    .req
    -0.06
    ç¿
    -0.06
    мп
    -0.06
    POSITIVE LOGITS
     infine
    0.09
    æľĢå¾Įãģ«
    0.08
    æľĢç»ĪçļĦ
    0.08
     concluding
    0.08
     Lastly
    0.08
    æľĢåIJİ
    0.08
     vali
    0.08
    æѤçĶŁ
    0.08
     concl
    0.08
    ä»Ĭå¾Įãģ®
    0.08
    Activations Density 0.792%

    No Known Activations