© 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. 56129
    Prev
    Next
    INDEX
    Explanations

    my followed by task or problem

    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
    人æĿ¥è¯´
    -0.09
    tmpl
    -0.08
    çļĦ人æĿ¥è¯´
    -0.08
    alti
    -0.07
    pper
    -0.07
    asename
    -0.07
    ä¸įéĤ£ä¹Ī
    -0.07
    æĪĸå¤ļ个
    -0.07
    å¿ħè¦ģæŶ
    -0.07
    åIJĪåIJĮæŶ
    -0.07
    POSITIVE LOGITS
    缮æłĩæĺ¯
    0.11
    ä»»åĬ¡æĺ¯
    0.09
     aim
    0.09
    磼
    0.09
     focus
    0.09
     goal
    0.09
    éĩįçĤ¹æĺ¯
    0.08
    缮çļĦæĺ¯
    0.08
    çłĶ究表æĺİ
    0.08
    å·¥ä½ľæĺ¯
    0.08
    Activations Density 0.166%

    No Known Activations