© 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. 10676
    Prev
    Next
    INDEX
    Explanations

    roots and powers

    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
    ίδ
    -0.07
    izzi
    -0.07
    çĥ¬
    -0.07
    åī©
    -0.07
    åĬ£åĬ¿
    -0.07
     Office
    -0.07
    æĢ»éĩı
    -0.06
    æĶ¿æ²»ä»»åĬ¡
    -0.06
    pike
    -0.06
    ä¸ºçĽ®çļĦ
    -0.06
    POSITIVE LOGITS
     squared
    0.08
    å¾µ
    0.07
    DIG
    0.07
    Squared
    0.07
    å¹³æĸ¹
    0.07
     Searches
    0.07
     Nearby
    0.07
    digit
    0.07
     squares
    0.07
     sqrt
    0.07
    Activations Density 0.006%

    No Known Activations