© 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. 17654
    Prev
    Next
    INDEX
    Explanations

    compute or calculate

    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
    ultipartFile
    -0.08
    ç»ıæŁ¥
    -0.08
    mund
    -0.08
    виÑĩ
    -0.07
    çĺª
    -0.07
     fondamentale
    -0.07
    微信åħ¬ä¼Ĺå¹³åı°
    -0.07
    åĪºæ¿ĢæĢ§é£Łçī©
    -0.07
    sters
    -0.07
    sts
    -0.07
    POSITIVE LOGITS
    æĸ°çļĦ
    0.07
    夫
    0.07
    并
    0.07
    æľĢä½³çļĦ
    0.06
    rap
    0.06
     trakcie
    0.06
    并ç»Ħç»ĩ
    0.06
    æĢ»åĮ»éĻ¢
    0.06
     appropriate
    0.06
    ilah
    0.06
    Activations Density 0.041%

    No Known Activations