© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57010
    Prev
    Next
    INDEX
    Explanations

    comparison 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
    γÏīγ
    -0.08
    culares
    -0.08
    ogany
    -0.07
    Globals
    -0.07
    stead
    -0.07
    ãĤ³ãĥł
    -0.07
    ähl
    -0.07
    好åѦ
    -0.07
    enticated
    -0.07
    shine
    -0.07
    POSITIVE LOGITS
    ï¸İ
    0.10
     Uncategorized
    0.07
    reet
    0.07
    -than
    0.07
    å¢Ł
    0.07
    rex
    0.07
    ejo
    0.07
    erne
    0.06
    ÑģÑĮ
    0.06
    åĴĮ大
    0.06
    Activations Density 0.102%

    No Known Activations