© 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. 27645
    Prev
    Next
    INDEX
    Explanations

    years, date ranges, financial periods

    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
    bou
    -0.07
    ноп
    -0.07
    _DAC
    -0.07
    ãĥ¬
    -0.07
    æıĴ
    -0.07
    ãĤ¯ãĥŃãĤ¹
    -0.07
    æ°¸çĶŁ
    -0.07
    æ³°
    -0.06
    ãĥĶãĤ¢
    -0.06
    bey
    -0.06
    POSITIVE LOGITS
    cius
    0.08
     Subtract
    0.08
    *Math
    0.07
    é¾Ļå±±
    0.07
    subtract
    0.07
    .Complete
    0.07
    ombine
    0.07
    veau
    0.07
    urnal
    0.07
    æ¯Ĺ
    0.07
    Activations Density 0.203%

    No Known Activations