© 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. 57279
    Prev
    Next
    INDEX
    Explanations

    quoting numbers

    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
    kampf
    -0.08
    çĻ»å½ķæŁ¥çľĭ
    -0.07
    ahan
    -0.07
    ña
    -0.07
    .vendor
    -0.07
    主æĮģä¼ļè®®
    -0.07
    kamp
    -0.07
    cim
    -0.07
    æŁ¥çľĭ详ç»Ĩ
    -0.07
    ihilation
    -0.07
    POSITIVE LOGITS
    Ñģлан
    0.07
    coe
    0.06
    ersi
    0.06
    俱ä¹IJéĥ¨
    0.06
    è²Ķ
    0.06
    оÑģÑĮ
    0.06
    åªĽ
    0.06
    (always
    0.06
    çī¹åĪ«æĺ¯åľ¨
    0.06
    prese
    0.06
    Activations Density 0.011%

    No Known Activations