© 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. 31722
    Prev
    Next
    INDEX
    Explanations

    showing relationships with lines and arrows

    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
    Âł
    -0.07
    ...
    -0.06
     ÑģÑĥв
    -0.06
     certain
    -0.06
    åºı
    -0.06
     Certain
    -0.06
     mal
    -0.06
     historically
    -0.06
    åľ¨æŁIJäºĽ
    -0.06
    åľ¨ä¼łç»Ł
    -0.06
    POSITIVE LOGITS
    示æĦı
    0.12
    表示
    0.10
    æĿ¥è¡¨ç¤º
    0.10
    åĪĻ表示
    0.10
     depiction
    0.10
     arrows
    0.09
    ä¹Łè¡¨ç¤º
    0.09
    以示
    0.09
     dashed
    0.09
    示
    0.09
    Activations Density 0.015%

    No Known Activations