© 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. 22848
    Prev
    Next
    INDEX
    Explanations

    not sure whether or why

    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
    çľĭçľĭåIJ§
    -0.09
    uite
    -0.07
    å¹´ç»ıéªĮ
    -0.07
    onomy
    -0.07
    gez
    -0.07
    éĤ
    -0.07
    åijĹ
    -0.07
    åĨµ
    -0.07
    ?):
    -0.07
    anced
    -0.07
    POSITIVE LOGITS
    æĺ¯åIJ¦æľī
    0.08
     whether
    0.08
    æĺ¯åIJ¦ä¸º
    0.07
    æĺ¯åIJ¦æĺ¯
    0.07
    æĺ¯è¯¥
    0.07
    æĺ¯åIJ¦ç¬¦åIJĪ
    0.07
    åĩĨç¡®æĢ§
    0.07
    ikkert
    0.07
    åħ·ä½ĵçļĦ
    0.07
     Whether
    0.07
    Activations Density 0.023%

    No Known Activations