© 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. 39775
    Prev
    Next
    INDEX
    Explanations

    prime factors

    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
    anke
    -0.07
    reak
    -0.07
    irurg
    -0.07
    urre
    -0.07
    anen
    -0.06
    çİĦå¹»å°ı说
    -0.06
    roker
    -0.06
    ê±´ìĿĺ
    -0.06
    ighth
    -0.06
    eenth
    -0.06
    POSITIVE LOGITS
    äºĨä¸ī
    0.09
    è¿Ļä¸ī
    0.08
    æľīä¸ī
    0.08
    tres
    0.08
    åĮ¹
    0.08
    åľ¨ä¸ī
    0.08
    大ä¸ī
    0.08
    çļĪ
    0.07
    åħ¶ä¸ī
    0.07
    zien
    0.07
    Activations Density 0.096%

    No Known Activations