© 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. 30532
    Prev
    Next
    INDEX
    Explanations

    on one hand

    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
    åħ¶ä¸ŃçļĦ
    -0.07
    okol
    -0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.07
    ambo
    -0.07
    olet
    -0.07
    æĸ¼æĺ¯
    -0.07
    etrieb
    -0.06
    ä»İèĢĮ使
    -0.06
    ع
    -0.06
    åħ¶ä¸ŃåĮħæĭ¬
    -0.06
    POSITIVE LOGITS
    åı¦ä¸Ģæĸ¹éĿ¢
    0.12
    erseits
    0.10
    åı¦ä¸Ģè¾¹
    0.09
    åİ¢
    0.09
    ìľ¼ë¡ľëĬĶ
    0.08
    åı¦ä¸Ģæĸ¹
    0.08
    -side
    0.08
     sisi
    0.08
     اÙĦآخر
    0.08
    ertes
    0.07
    Activations Density 0.052%

    No Known Activations