© 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. 17823
    Prev
    Next
    INDEX
    Explanations

    sand and sandy contexts

    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
    anni
    -0.09
    Ñīенко
    -0.08
     cider
    -0.08
    걸
    -0.07
    ลฯ
    -0.07
    çīº
    -0.07
    ê»ı
    -0.07
    æĿ¥è¶Ĭ
    -0.07
    çĬ§
    -0.07
    èĢĮ代ä¹ĭ
    -0.07
    POSITIVE LOGITS
    à¸Ĺราย
    0.11
    ier
    0.10
    stone
    0.09
     mouv
    0.08
    iera
    0.08
    æ²ĻåŃIJ
    0.08
    wich
    0.08
    æ²Ļ滩
    0.07
    sterol
    0.07
     اÙĦرÙħÙĦ
    0.07
    Activations Density 0.025%

    No Known Activations