© 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. 23065
    Prev
    Next
    INDEX
    Explanations

    publications series titles

    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
    agna
    -0.09
    lish
    -0.09
     Diario
    -0.08
    ANH
    -0.08
    uard
    -0.08
     DISABLE
    -0.08
    ีà¸Ķ
    -0.08
    æ²¹çĽIJ
    -0.07
    ä¸īåı£
    -0.07
    ghan
    -0.07
    POSITIVE LOGITS
     series
    0.08
     serii
    0.08
    ä¸Ľä¹¦
    0.08
    ç³»åĪĹ
    0.07
    -series
    0.07
     ÑģеÑĢии
    0.07
    ç¼ĸåı·
    0.07
    åı·
    0.07
    éĢĿ
    0.06
    .library
    0.06
    Activations Density 0.078%

    No Known Activations