© 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. 10484
    Prev
    Next
    INDEX
    Explanations

    if ... then

    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
    ÑĢенÑĮ
    -0.09
     herself
    -0.08
    åIJĪåIJĮæŶ
    -0.08
    astique
    -0.08
    }{$
    -0.08
     Strec
    -0.08
     Yourself
    -0.08
     withd
    -0.08
     thus
    -0.08
    æīĢ以她
    -0.08
    POSITIVE LOGITS
     there
    0.09
    ...
    0.07
     it
    0.07
    æķ´ä¸ª
    0.07
    it
    0.07
    å®ĥå°±æĺ¯
    0.07
    there
    0.07
    ify
    0.07
    å®ĥ
    0.07
    åĩºäºİ
    0.07
    Activations Density 0.012%

    No Known Activations