© 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. 10335
    Prev
    Next
    INDEX
    Explanations

    no longer or not anymore

    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
    ä¸įä»ħæľī
    -0.09
     nejen
    -0.08
    èĻ½çĦ¶ä¸įæĺ¯
    -0.08
     ÏĮÏĩι
    -0.08
     not
    -0.08
     NOT
    -0.08
    ä½Ĩä¸įæĺ¯
    -0.07
    笤
    -0.07
    èĢĮä¸įæĺ¯
    -0.07
    ä¸įä»ħåľ¨
    -0.07
    POSITIVE LOGITS
     nor
    0.20
    èĢĮæĺ¯
    0.18
    èĢĮæĺ¯è¦ģ
    0.17
     anymore
    0.16
     melainkan
    0.16
     sondern
    0.15
    èĢĮæĺ¯åľ¨
    0.14
    èĢĮæĺ¯åĽłä¸º
    0.14
    หรà¸Ńà¸ģ
    0.13
     Nor
    0.13
    Activations Density 0.539%

    No Known Activations