© 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. 10992
    Prev
    Next
    INDEX
    Explanations

    Fe or RTK

    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
    å¤§åľ£
    -0.07
    orris
    -0.07
    chino
    -0.07
    è¯Ĺç¯ĩ
    -0.07
    äºİæĺ¯ä»ĸ
    -0.07
    åŃ¦å¼Ł
    -0.07
    .broadcast
    -0.07
    cion
    -0.06
    å¸Ĥä¸Ń
    -0.06
    讲æĶ¿æ²»
    -0.06
    POSITIVE LOGITS
     appunto
    0.09
    æ£ł
    0.07
    leftright
    0.07
    lems
    0.07
    æŀľçĦ¶
    0.07
     indeed
    0.07
    éĻįä½İæĪIJæľ¬
    0.06
    ä¸įè¨ĢèĢĮåĸ»
    0.06
    ome
    0.06
    áro
    0.06
    Activations Density 0.009%

    No Known Activations