© 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. 32592
    Prev
    Next
    INDEX
    Explanations

    keywords and code endings

    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
     <![
    -0.09
    åı¯æ¢¦
    -0.08
    åĢ©
    -0.08
      č↵
    -0.07
    ç½Ĺåħ°
    -0.07
    åĩŃä»Ģä¹Ī
    -0.07
    <|fim_prefix|>
    -0.07
    æŶèĩ³ä»Ĭ
    -0.07
    č↵
    -0.07
     č↵
    -0.07
    POSITIVE LOGITS
    åı¦å¤ĸä¸Ģç§į
    0.09
    缸åħ³éĹ®çŃĶ
    0.07
    åĢ¼å¾Ĺä¸ĢæıIJçļĦæĺ¯
    0.07
    alion
    0.07
    ÙĦاÙģ
    0.06
     additionally
    0.06
    è¿Ŀåıįä¸Ĭè¿°
    0.06
    ä¸įæİĴéĻ¤
    0.06
    对åħ¶ä»ĸ
    0.06
    éĻ¤æѤä¹ĭå¤ĸ
    0.06
    Activations Density 0.139%

    No Known Activations