© 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. 11785
    Prev
    Next
    INDEX
    Explanations

    is, was, being, or seemed

    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
    ä»İ没
    -0.08
    åŃĺåľ¨ä¸Ģå®ļçļĦ
    -0.08
    áºł
    -0.08
    iad
    -0.07
    ä»ħä»£è¡¨ä½ľèĢħ
    -0.07
     ê³
    -0.07
    uang
    -0.07
    :int
    -0.07
    ockey
    -0.07
    éĩįè¦ģçļĦæĺ¯
    -0.07
    POSITIVE LOGITS
    æĺ¯æľĢ
    0.09
    æĺ¯åĶ¯ä¸Ģ
    0.08
    lee
    0.08
    ittest
    0.08
     Ø£ÙĪÙĦÙī
    0.07
     preferable
    0.07
    åļ
    0.07
    èĥľåĩº
    0.07
    为ä¸Ĭ
    0.07
    å½ĵä¹ĭ
    0.07
    Activations Density 0.074%

    No Known Activations