© 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. 19718
    Prev
    Next
    INDEX
    Explanations

    difference or combination

    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
    adoo
    -0.09
    å¤ļ空
    -0.09
    adop
    -0.08
    lickr
    -0.08
    urlencode
    -0.08
    åĬĽä½ľ
    -0.08
    _SUR
    -0.08
    WindowState
    -0.08
    è¿Ľè¡Įæµĭè¯ķ
    -0.08
    ÙħÙĪد
    -0.08
    POSITIVE LOGITS
    æ¶Ī
    0.08
    æĴĩ
    0.07
    z
    0.06
    element
    0.06
     seg
    0.06
    æĸ°æľĪ
    0.06
    è¿IJ
    0.06
     eliminates
    0.06
    -ton
    0.06
    æĺİ
    0.06
    Activations Density 0.002%

    No Known Activations