© 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. 9875
    Prev
    Next
    INDEX
    Explanations

    say / suppose / hypothetical

    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
    abyrin
    -0.08
    æīįå¾Ĺ以
    -0.08
    æĪijåı¯æĺ¯
    -0.07
    å¿ħè¦ģæŶ
    -0.07
    çijŀæĭī
    -0.07
    fois
    -0.07
    asaan
    -0.07
    æĪijçļĦ人
    -0.07
    åı¯æľĽ
    -0.07
    åİ»ä½ķ
    -0.07
    POSITIVE LOGITS
    æŁIJä¸Ģ天
    0.10
     hypoth
    0.10
     hypothetical
    0.10
     suppose
    0.10
    æŁIJ天
    0.10
     Suppose
    0.09
    çªģçĦ¶åıijçİ°
    0.09
    è¿Ļæł·ä¸Ģç§į
    0.09
     suddenly
    0.09
    æŁIJ
    0.09
    Activations Density 0.500%

    No Known Activations