© 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. 47702
    Prev
    Next
    INDEX
    Explanations

    still plus verb

    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
    å¹³æĻĤ
    -0.08
    å¹³æŶ
    -0.08
    åıĪæĺ¯
    -0.08
    ãģĤãĤīãģĭãģĺãĤģ
    -0.08
    ä¸Ģå¼Ģå§ĭ
    -0.08
    äºĭåħĪ
    -0.07
    åıĪä¸į
    -0.07
    é¢ĦåħĪ
    -0.07
    æľ¬æĿ¥å°±
    -0.07
    ä¸Ģæ°Ĺãģ«
    -0.07
    POSITIVE LOGITS
     ìŬìłĦíŀĪ
    0.18
    ä¾ĿçĦ¶
    0.18
    ä»įæľī
    0.18
    ä»įçĦ¶
    0.17
    ä»įçĦ¶åŃĺåľ¨
    0.17
    ä¾Ŀæŧ
    0.17
    ä¾ĿçĦ¶åŃĺåľ¨
    0.17
    ä»įæľª
    0.17
    still
    0.16
    ä»į
    0.16
    Activations Density 0.412%

    No Known Activations