© 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. 64532
    Prev
    Next
    INDEX
    Explanations

    unique or distinct items

    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
     buffered
    -0.08
    Buf
    -0.07
     pappa
    -0.07
    ibert
    -0.07
    _classification
    -0.07
    idence
    -0.07
    æĺ¥æļĸèĬ±å¼Ģ
    -0.07
    èĢģçĪ¹
    -0.07
    åİŁä½ĵ
    -0.07
     Mois
    -0.07
    POSITIVE LOGITS
     unused
    0.08
     unique
    0.08
    æ±łä¸Ń
    0.07
     distinct
    0.07
     ê³łìľł
    0.07
     Mandatory
    0.07
    çĭ¬ä¸ĢæĹłäºĮçļĦ
    0.07
    _POOL
    0.07
     UNIQUE
    0.07
    æ±ł
    0.07
    Activations Density 0.008%

    No Known Activations