© 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. 3468
    Prev
    Next
    INDEX
    Explanations

    in doing so

    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
    ijan
    -0.08
    tis
    -0.07
    ovice
    -0.07
    æĦıåľ¨
    -0.07
    udies
    -0.07
    ersatz
    -0.07
    colari
    -0.06
    allet
    -0.06
    缸å¾ħ
    -0.06
    ifications
    -0.06
    POSITIVE LOGITS
    ç¨ĭ度ä¸Ĭ
    0.09
    ä¹ĭä½Ļ
    0.08
    çļĦæŶåĢĻä¼ļ
    0.08
    çļĦæŶåĢĻåı¯ä»¥
    0.08
    ä¸Ńå¾ĹåĪ°
    0.08
    ä¹ĭåīįå°±
    0.08
    åīįåħĪ
    0.07
    çļĦè¿ĩç¨ĭä¸Ń
    0.07
    ä¸Ńåıijçİ°
    0.07
    çļĦæŶåĢĻä¸Ģå®ļè¦ģ
    0.07
    Activations Density 0.020%

    No Known Activations