© 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. 64683
    Prev
    Next
    INDEX
    Explanations

    actions after an event

    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
    reira
    -0.08
    ãĥ«ãĥĪ
    -0.08
    æīĵæ¶Ī
    -0.08
    åĸĥ
    -0.08
    ç£
    -0.07
    æĹ¥æ¶Īæģ¯
    -0.07
    oola
    -0.07
    ãģ¤ãģ¤
    -0.07
    ierre
    -0.07
    ç«¯æľ¨
    -0.07
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.09
    åı¦è¡Į
    0.09
    æĪĸåħ¶å®ĥ
    0.08
    æĪĸåħ¶ä»ĸ
    0.07
    åħ¶ä»ĸ
    0.07
     further
    0.07
    åı¦å¤ĸä¸Ģ个
    0.07
    声èī²
    0.07
    åı¦
    0.07
    æľ¬å°±
    0.07
    Activations Density 0.138%

    No Known Activations