© 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. 43038
    Prev
    Next
    INDEX
    Explanations

    lists of options or layers

    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
    æ°¸
    -0.07
    æ°¸çĶŁ
    -0.07
    ãĢİ
    -0.07
     originals
    -0.06
    eu
    -0.06
    幸
    -0.06
     Cand
    -0.06
    æĸ¹èĪŁ
    -0.06
     mai
    -0.06
    isson
    -0.06
    POSITIVE LOGITS
    åİķ
    0.07
    åIJįæĢĿ
    0.07
    IDD
    0.07
    IMIT
    0.07
    åľ¨èģĮçłĶ究çĶŁ
    0.07
    åĨłçĬ¶çĹħæ¯Ĵ
    0.07
    opan
    0.07
     comod
    0.07
    èĥŃ
    0.07
    æı©
    0.07
    Activations Density 0.022%

    No Known Activations