© 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. 46163
    Prev
    Next
    INDEX
    Explanations

    time zones and times

    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
     instanceof
    -0.08
    çĩĥçĥ§çļĦ
    -0.08
    åĪĨéĴŁåīį
    -0.07
    è°ģçļĦ
    -0.07
    ×ŀר
    -0.07
    rette
    -0.06
    abol
    -0.06
    ÑĨе
    -0.06
    à¹Ģà¸ķà¸Ńรà¹Į
    -0.06
    æĢªçļĦ
    -0.06
    POSITIVE LOGITS
    pek
    0.08
    对åºĶ
    0.08
    Equivalent
    0.08
    áĢ¬
    0.08
    IRT
    0.07
     equivalents
    0.07
     equivalent
    0.07
    çŃīæķĪ
    0.07
    .testing
    0.07
    ,__
    0.07
    Activations Density 0.150%

    No Known Activations