© 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. 4528
    Prev
    Next
    INDEX
    Explanations

    .js file suffixes

    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
     unlock
    -0.07
    çīĻ
    -0.06
    群
    -0.06
    orda
    -0.06
    æĥł
    -0.06
    æ··
    -0.06
    ä¹ĭ
    -0.06
    {@
    -0.06
    ord
    -0.06
    licit
    -0.06
    POSITIVE LOGITS
    è¿Ļéĥ¨åĪĨ
    0.08
    éĥ¨åĪĨç»ĦæĪIJ
    0.08
    uolo
    0.08
     kısm
    0.07
    entifier
    0.07
    士ãģ®
    0.07
    gau
    0.07
    å±ŀäºİä½łçļĦ
    0.07
    ARGIN
    0.07
     Matcher
    0.07
    Activations Density 0.010%

    No Known Activations