© 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. 40539
    Prev
    Next
    INDEX
    Explanations

    ratio, Canonical, Self

    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
    ç»´çĶŁç´łåĴĮ
    -0.07
    ?type
    -0.07
    éĢļãĤĬ
    -0.06
    ampion
    -0.06
    åºĹãģ¯
    -0.06
    /version
    -0.06
    uale
    -0.06
    çĶµçº¿çĶµç¼Ĩ
    -0.06
    æĹ©åıijçİ°
    -0.06
    macher
    -0.06
    POSITIVE LOGITS
    earer
    0.08
    æĸ°æľĪ
    0.08
    åľ°çĵľ
    0.07
    åIJIJåĩº
    0.07
    onnier
    0.07
    æľīæķĪ
    0.07
    ymoon
    0.07
    éĢĨåIJij
    0.07
     $('[
    0.07
    aksi
    0.07
    Activations Density 0.008%

    No Known Activations