© 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. 26197
    Prev
    Next
    INDEX
    Explanations

    code discussion

    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
    éĢļçŁ¥æĪij们
    -0.07
    é½Ĵ
    -0.07
    ึà¸ĩ
    -0.07
    ä¸įè°ĥ
    -0.07
     consigo
    -0.07
    MouseButton
    -0.07
    lobs
    -0.07
    emouth
    -0.07
    pris
    -0.07
    (IP
    -0.06
    POSITIVE LOGITS
     comment
    0.09
    åĪĨæŀIJ
    0.09
    论述
    0.08
    åĪ¤æĸŃé¢ĺ
    0.08
    论è¯ģ
    0.08
    éĻĪè¿°
    0.08
    è¯Ħ论
    0.08
     documentation
    0.08
     editorial
    0.08
     sottoline
    0.08
    Activations Density 1.872%

    No Known Activations