© 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. 47805
    Prev
    Next
    INDEX
    Explanations

    list of ordered 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
    éĻIJåĪ¶çļĦ
    -0.07
     ham
    -0.07
    ży
    -0.07
    ÙİÙĨÙIJ
    -0.07
    ottes
    -0.06
    anford
    -0.06
    ç¼Ī
    -0.06
    irection
    -0.06
    Multiplier
    -0.06
     huis
    -0.06
    POSITIVE LOGITS
    åºŁ
    0.08
    ä¸ĭä¸Ģ个
    0.08
    å¾Ĺ罪
    0.07
    继ç»Ń
    0.07
    OTO
    0.07
     Donovan
    0.07
    廢
    0.07
    bens
    0.07
    ters
    0.07
    éĢIJä¸Ģ
    0.07
    Activations Density 0.006%

    No Known Activations