© 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. 2595
    Prev
    Next
    INDEX
    Explanations

    questions about using

    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
    ptest
    -0.07
    è¿ĻçĤ¹
    -0.07
    kof
    -0.07
    ugen
    -0.07
    æ¯ķç«Ł
    -0.06
     \`
    -0.06
    itual
    -0.06
     Retreat
    -0.06
    åĽłä¸ºå¥¹
    -0.06
     ÙĦات
    -0.06
    POSITIVE LOGITS
    潺
    0.07
    orarily
    0.07
    EntityType
    0.07
    uplicate
    0.07
    ine
    0.07
    umably
    0.07
    大åĪ©
    0.06
    èIJĮèIJĮ
    0.06
    çĴĭ
    0.06
    ÏĦÏģ
    0.06
    Activations Density 0.005%

    No Known Activations