© 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. 43721
    Prev
    Next
    INDEX
    Explanations

    still not understood

    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
    SEM
    -0.08
    æľ¬æĿ¥
    -0.08
    å¹³æŶ
    -0.08
    ä¸įæį¢
    -0.08
    ä½Ĩä¸į
    -0.07
    没æľīå¿ħè¦ģ
    -0.07
     irrelevant
    -0.07
    iw
    -0.07
    æĹłéľĢ
    -0.07
    ä¸įçĶ¨åĨį
    -0.07
    POSITIVE LOGITS
    å°ļæľª
    0.15
    缮åīįçļĦ
    0.14
    å°ļ
    0.14
     ìķĦì§ģ
    0.14
    æľīå¾ħ
    0.14
    å°ļæĹł
    0.14
    缮åīį
    0.13
    ä»įå¤Ħäºİ
    0.12
    缮åīįæĺ¯
    0.12
    缮åīį没æľī
    0.12
    Activations Density 0.486%

    No Known Activations