© 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. 32818
    Prev
    Next
    INDEX
    Explanations

    possibility or uncertainty

    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
     accordingly
    -0.08
    lah
    -0.08
    hya
    -0.08
    èĬª
    -0.08
    å¾Īåı¯èĥ½
    -0.07
    anter
    -0.07
    many
    -0.07
    å¦Ĭ
    -0.07
    oft
    -0.07
    ookies
    -0.07
    POSITIVE LOGITS
     somehow
    0.13
     irgendwie
    0.08
     Somehow
    0.08
    æĹłæĦıä¸Ń
    0.07
    çļĦåħ¶ä»ĸ
    0.07
    åħ¶ä»ĸåľ°æĸ¹
    0.07
    ëĿ¼ëıĦ
    0.07
     accidentally
    0.07
    endo
    0.07
    åħ¶ä»ĸ
    0.07
    Activations Density 0.040%

    No Known Activations