© 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. 64137
    Prev
    Next
    INDEX
    Explanations

    time indicators and local qualifiers

    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
    antin
    -0.08
    vron
    -0.08
    ADER
    -0.08
    æŁ¥çľĭ详ç»Ĩ
    -0.08
    MediaType
    -0.08
    纾
    -0.08
    ufe
    -0.07
    tar
    -0.07
    Õ²
    -0.07
    igor
    -0.07
    POSITIVE LOGITS
    æīį对
    0.08
    代ä¹ĭ
    0.07
    hus
    0.07
    aura
    0.06
    egas
    0.06
    大马
    0.06
    dddd
    0.06
    infeld
    0.06
    åľ¨ä½ı
    0.06
    ment
    0.05
    Activations Density 0.021%

    No Known Activations