© 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. 18270
    Prev
    Next
    INDEX
    Explanations

    guides and blogs

    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
    ç¡®æľī
    -0.10
    åĨįæľī
    -0.07
     ÙħÛĮÙĦ
    -0.07
    alytics
    -0.07
    订éĺħä¸ĵæłı
    -0.07
    -NLS
    -0.07
    orti
    -0.07
    räf
    -0.07
    éĥ½èĥ½åľ¨
    -0.07
    幸ç¦ıçĶŁæ´»
    -0.07
    POSITIVE LOGITS
    VF
    0.07
    æĨ¬
    0.07
    ä»Ģä¹Īéĥ½ä¸į
    0.07
    ä¸įå®Įæķ´
    0.07
    åı¯ä»¥çĶ¨æĿ¥
    0.07
    æ¶ħ
    0.06
    ä»Ģä¹Īéĥ½æ²¡æľī
    0.06
    µ¬
    0.06
    ç¼ĸ
    0.06
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.06
    Activations Density 0.041%

    No Known Activations