© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18052
    Prev
    Next
    INDEX
    Explanations

    list operations and range

    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
    jenigen
    -0.08
    ä¸İå®ŀéĻħ
    -0.07
    ansson
    -0.07
    æĽ´å¤ļ精彩
    -0.07
    åĪ¶å®ļåĩº
    -0.07
    orch
    -0.06
    ливо
    -0.06
    tlement
    -0.06
    orrh
    -0.06
    utterstock
    -0.06
    POSITIVE LOGITS
    omis
    0.07
    nty
    0.07
    zun
    0.07
    æľºèĥ½
    0.07
    hend
    0.07
    ä¹ĭæĢ¥
    0.07
    azen
    0.07
     dáºŃp
    0.07
    å·Ŀ
    0.06
    滨河
    0.06
    Activations Density 0.001%

    No Known Activations