© 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. 21734
    Prev
    Next
    INDEX
    Explanations

    statistical terms and concepts

    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
     pro
    -0.07
    UP
    -0.07
     impart
    -0.06
    è¡¥éĴĻ
    -0.06
     rig
    -0.06
     mag
    -0.06
    ITU
    -0.06
     stimulating
    -0.06
    èĩªè§īéģµå®Ī
    -0.06
    XA
    -0.06
    POSITIVE LOGITS
     pooled
    0.08
    ooled
    0.08
    æ»ĭ
    0.08
    çŃł
    0.08
    .gui
    0.08
     residuals
    0.08
    què
    0.07
    _helpers
    0.07
    å¹³åĿĩæ¯ı
    0.07
    ikota
    0.07
    Activations Density 0.002%

    No Known Activations