© 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. 45866
    Prev
    Next
    INDEX
    Explanations

    evening and time of day

    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
    ÑģмоÑĤÑĢиÑĤе
    -0.09
    åĽłä¸ºæĺ¯
    -0.08
    ÙĴÙĨ
    -0.08
    acon
    -0.08
    eworld
    -0.08
     Monteiro
    -0.08
     madrug
    -0.07
    leman
    -0.07
    /control
    -0.07
    ergestellt
    -0.07
    POSITIVE LOGITS
    most
    0.07
    гей
    0.07
    æŶåĪĨ
    0.07
    à¹Īาย
    0.07
    å¤ķ
    0.07
     tardi
    0.07
    ormal
    0.06
    /l
    0.06
    گاÙĩÛĮ
    0.06
    veil
    0.06
    Activations Density 0.088%

    No Known Activations