© 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. 48898
    Prev
    Next
    INDEX
    Explanations

    be followed by the or a

    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
    æ¯ıä¸Ģ个人çļĦ
    -0.08
    éĹ®é¢ĺæĺ¯
    -0.07
    جاز
    -0.07
    åİī害äºĨ
    -0.07
    åħĭæĸ¯
    -0.07
    éĹ®é¢ĺè¿Ľè¡Į
    -0.07
    åģļäºĽä»Ģä¹Ī
    -0.07
    æ¯ıä¸Ģ个人
    -0.07
    æ¢ħæŀĹ
    -0.07
    åĬŁäºİ
    -0.07
    POSITIVE LOGITS
     the
    0.10
    elyn
    0.08
    aset
    0.08
    asser
    0.07
    ely
    0.07
     اÛĮÙĨÚ©Ùĩ
    0.07
    emente
    0.07
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.06
    atera
    0.06
    ethe
    0.06
    Activations Density 0.032%

    No Known Activations