© 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. 48199
    Prev
    Next
    INDEX
    Explanations

    method calls and comparisons

    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
    èĢĮä¸Ķæĺ¯
    -0.08
    à¸ģà¹ĩà¹Ħà¸Ķà¹ī
    -0.07
    ov
    -0.07
    åĵī
    -0.07
    è¿Ļä¹Īç®Ģåįķ
    -0.06
    ÙİÙĨÙIJ
    -0.06
    ovia
    -0.06
     ov
    -0.06
    ä¹Łå°±æĦıåij³çĿĢ
    -0.06
    éļ¾æĢª
    -0.06
    POSITIVE LOGITS
    çļĦè¯Ħä»·æĺ¯
    0.09
    ")==
    0.09
    )==
    0.08
    npos
    0.08
    ')==
    0.08
    å·®ä¸į
    0.08
    çļĦä¸ĢåĪĩéĥ½
    0.08
    ))==
    0.07
     yra
    0.07
     dalje
    0.07
    Activations Density 0.040%

    No Known Activations