© 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. 60535
    Prev
    Next
    INDEX
    Explanations

    past time references

    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
    currently
    -0.08
    ival
    -0.07
     currently
    -0.07
    Currently
    -0.07
    ãĤĪãģĨãģ«ãģªãĤĬãģ¾ãģĹãģŁ
    -0.07
    itters
    -0.07
    usually
    -0.07
    æĺ¾å¾ĹæĽ´åĬł
    -0.07
    æĬĢ
    -0.07
    Usually
    -0.07
    POSITIVE LOGITS
     recentemente
    0.13
     recently
    0.13
     ayer
    0.12
     volna
    0.12
     вÑĩеÑĢа
    0.12
    /is
    0.11
     ontem
    0.11
     previously
    0.11
     originally
    0.11
     récemment
    0.11
    Activations Density 1.061%

    No Known Activations