© 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. 28487
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with variables and symbols

    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
    ingt
    -0.08
     Vidal
    -0.08
    ersp
    -0.07
    /gen
    -0.06
     eng
    -0.06
    éĽķ
    -0.06
    èĮĹ
    -0.06
    oom
    -0.06
    .Gen
    -0.06
    ابة
    -0.06
    POSITIVE LOGITS
    иÑģÑĤо
    0.08
    κÏģα
    0.08
    cott
    0.08
    aviolet
    0.07
     payday
    0.07
    WithValue
    0.07
    åĪĨ离
    0.07
    Õµ
    0.07
    Ä«g
    0.07
    æī«äºĮç»´çłģ
    0.07
    Activations Density 0.004%

    No Known Activations