© 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. 14650
    Prev
    Next
    INDEX
    Explanations

    divides / of / from sequences

    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
    asic
    -0.08
    raw
    -0.07
    æĥħåĨµè¿Ľè¡ĮäºĨ
    -0.07
    гелÑĮ
    -0.07
    uhu
    -0.07
    è¯ŀè¾°
    -0.07
    orum
    -0.07
    ä½ľä¸ºä¸ĢåIJį
    -0.07
    ä½ľä¸ºä¸Ģ项
    -0.07
    lias
    -0.07
    POSITIVE LOGITS
    åįģäºĮçĶŁèĤĸ
    0.07
    ÃŃp
    0.07
    ä¸Ķ
    0.07
     confines
    0.07
    åħ¸å½ĵ
    0.07
    è¾ľ
    0.06
    è¡Į为
    0.06
    ç´§
    0.06
    ç¯ĵ
    0.06
    æŀ¶
    0.06
    Activations Density 0.007%

    No Known Activations