© 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. 14807
    Prev
    Next
    INDEX
    Explanations

    adducts, isomerize, dichloro, cyclic metabolite, reduced

    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
    æĹłè®ºä»İ
    -0.07
     hopefully
    -0.07
    ç»Ŀ大éĥ¨åĪĨ
    -0.07
     ìĪĺë°ĸìĹIJ
    -0.07
    åħĭæľį
    -0.07
    IMUM
    -0.07
     thankfully
    -0.06
     overwhelmingly
    -0.06
    æĹłè®ºåľ¨
    -0.06
    ervis
    -0.06
    POSITIVE LOGITS
    诸å¦Ĥ
    0.10
     somehow
    0.09
    类似
    0.08
    人æĪĸ
    0.08
     temporarily
    0.08
    æĬķèµĦæĪĸ
    0.08
    类似äºİ
    0.08
    æĪĸåĪ©çĶ¨
    0.08
    类似çļĦ
    0.08
    å¤ĦçIJĨåIJİ
    0.08
    Activations Density 0.013%

    No Known Activations