© 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. 27136
    Prev
    Next
    INDEX
    Explanations

    prime factors and divisibility

    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
    æ·ĭ
    -0.07
    éĵ¶
    -0.07
    è¿ľæµģ
    -0.07
     rinse
    -0.07
    ä¹īåĭĩ
    -0.07
    alin
    -0.07
    éļıçĿĢ
    -0.06
     Bao
    -0.06
    allery
    -0.06
    vern
    -0.06
    POSITIVE LOGITS
    è¯ķçĿĢ
    0.08
    hop
    0.08
    è¯ķæİ¢
    0.08
    ooks
    0.07
    Disclosure
    0.07
    Dear
    0.07
    对å®ĥ
    0.07
    iho
    0.07
    à¹īว
    0.07
    æľīåı¯èĥ½æĺ¯
    0.07
    Activations Density 0.009%

    No Known Activations