© 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. 49906
    Prev
    Next
    INDEX
    Explanations

    quantitation, estimation, number, abundance

    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
    acher
    -0.07
    åºĶå¾ģ
    -0.07
    BW
    -0.07
    ä¼ģä¸ļæ³ķ人
    -0.07
    ãĤŃãĥ£
    -0.07
    egan
    -0.06
    人çĶŁ
    -0.06
    xia
    -0.06
    anning
    -0.06
    çĤĻ
    -0.06
    POSITIVE LOGITS
    ç´°ç¯Ģ
    0.07
    ç»Ĩèĩ´
    0.07
    è¿Ľä¸ĢæŃ¥çļĦ
    0.07
     ìĦ¸ë¶Ģ
    0.07
     detailed
    0.07
    è¿Ľä¸ĢæŃ¥ä¼ĺåĮĸ
    0.07
    TRACE
    0.07
    详
    0.07
    åħ·ä½ĵæŶéĹ´
    0.07
    æľīå¤ļ
    0.07
    Activations Density 0.209%

    No Known Activations