© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49071
    Prev
    Next
    INDEX
    Explanations

    suffix combinations

    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
    ably
    -0.07
    Aws
    -0.07
    atee
    -0.07
    abler
    -0.06
    liš
    -0.06
    箸
    -0.06
    zien
    -0.06
    ftime
    -0.06
    鸳
    -0.06
    cheid
    -0.06
    POSITIVE LOGITS
    å¦Ĥæľīä¾µæĿĥ
    0.08
    ç»Ļ大家æݨèįIJ
    0.07
    æ²³æµģåŁŁ
    0.07
    Ñĩенко
    0.07
    å¾ĭå¸ĪäºĭåĬ¡æīĢå¾ĭå¸Ī
    0.07
    éľīç´ł
    0.07
    å±±æĻ¯åĮº
    0.07
     Umg
    0.07
    à¸ļุรี
    0.06
    ylum
    0.06
    Activations Density 0.998%

    No Known Activations