© 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. 63902
    Prev
    Next
    INDEX
    Explanations

    selection, outcome, site, recipient, partitions

    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
    agre
    -0.08
     bud
    -0.08
    hare
    -0.08
    angers
    -0.08
    æĺ¥å¤ıç§ĭåĨ¬
    -0.07
    ä¸Ĭå¸ĤåIJİ
    -0.07
    éĩįçĤ¹ä»»åĬ¡
    -0.07
    为å®ĹæŨ
    -0.07
    indre
    -0.06
    studi
    -0.06
    POSITIVE LOGITS
     consisted
    0.08
    è¦ģä¹Īæĺ¯
    0.07
    åĬ¨åĬĽæĸ¹éĿ¢
    0.07
    either
    0.07
     either
    0.07
    åĩĨå¤ĩ
    0.07
     Ø¥Ùħا
    0.07
    æĸ¹éĿ¢
    0.07
    urr
    0.07
     hardest
    0.07
    Activations Density 0.101%

    No Known Activations