© 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. 21735
    Prev
    Next
    INDEX
    Explanations

    programming concepts and keywords

    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
    æĪijæĦ¿
    -0.08
    /
    -0.06
    究竣
    -0.06
    羯
    -0.06
     nod
    -0.06
    éĻį
    -0.06
    awa
    -0.06
    udence
    -0.06
    ulse
    -0.06
    /src
    -0.06
    POSITIVE LOGITS
    _SIMPLE
    0.09
    æ¯Ķè¾ĥç®Ģåįķ
    0.09
    plast
    0.09
    unks
    0.08
    ç®Ģç®Ģåįķ
    0.08
    icont
    0.08
    éŁ³åĥı
    0.08
    Cls
    0.08
    æĥŁä¸Ģ
    0.08
    pa
    0.08
    Activations Density 0.002%

    No Known Activations