© 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. 23404
    Prev
    Next
    INDEX
    Explanations

    counting frequency and histograms

    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
    ÑĤика
    -0.07
    ä¿¡çĶ¨è¯Ħ级
    -0.07
     Wunder
    -0.06
    é£İ
    -0.06
    à¹īาà¸Ļ
    -0.06
    ALLOW
    -0.06
    allow
    -0.06
    wein
    -0.06
    altung
    -0.06
    çİ°
    -0.06
    POSITIVE LOGITS
    counts
    0.11
     counts
    0.11
    .getCount
    0.09
     Counts
    0.09
    =count
    0.09
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.09
    Counts
    0.08
    æ¯ıç§į
    0.08
    ç»Łè®¡è¡¨
    0.08
     count
    0.08
    Activations Density 0.061%

    No Known Activations