© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61806
    Prev
    Next
    INDEX
    Explanations

    plotted against

    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¸Ģåľ°
    -0.08
    ä¸ĭ载使çĶ¨
    -0.07
    åĿ¤
    -0.07
    ä¸įå¾Ĺä»İäºĭ
    -0.07
    åħĪæĺ¯
    -0.07
    æł¸
    -0.06
    ä¸ºåĽ½
    -0.06
    èĥ½éĢĤåºĶ
    -0.06
     Lindsey
    -0.06
    度
    -0.06
    POSITIVE LOGITS
    ickest
    0.09
    ä¸Ńæī¾åĪ°
    0.08
    ãģ®ä¸ŃãģĭãĤī
    0.08
    æĢ»ä¼ļæľī
    0.07
    sett
    0.07
    ubern
    0.07
    çļĦé¦ĸ
    0.07
    ä¹ĭå®Ŀ
    0.07
    ozilla
    0.07
    汪æ´ĭ
    0.07
    Activations Density 0.169%

    No Known Activations