© 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. 31563
    Prev
    Next
    INDEX
    Explanations

    non-word characters

    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
    以ä¸ĭæĿ¡ä»¶
    -0.07
    ãģ§ãģĻãĤĪ
    -0.07
    åģ¿
    -0.07
    æĺ¾èijĹæıIJé«ĺ
    -0.06
    ãģ§ãģĻãģ®ãģ§
    -0.06
    leben
    -0.06
    åĨį继ç»Ń
    -0.06
    ç¥ī
    -0.06
    æľĢæĸ°æĸĩç«ł
    -0.06
    å¦Ĥåħ¶
    -0.06
    POSITIVE LOGITS
    ä½Ĩåħ¶å®ŀ
    0.13
     ÑıкобÑĭ
    0.12
    æ®Ĭä¸įçŁ¥
    0.11
    ä½Ĩå®ŀéĻħä¸Ĭ
    0.11
    åħ¶å®ŀ
    0.10
     padahal
    0.10
    ä¹į
    0.09
    åħ¶å®ŀåľ¨
    0.09
    åħ¶å¯¦
    0.09
     rightly
    0.09
    Activations Density 0.234%

    No Known Activations