© 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. 33128
    Prev
    Next
    INDEX
    Explanations

    expected probability

    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
    çĽĺçļĦ
    -0.08
    меÑĤи
    -0.07
    没æľīæŶéĹ´
    -0.07
    groupName
    -0.07
    [^
    -0.07
    é¢ĨåŁŁä¸Ń
    -0.07
    åľ¨ä¼Ĺå¤ļ
    -0.07
    ç¬ĥ
    -0.07
    æľīä½Ļ
    -0.07
    inator
    -0.07
    POSITIVE LOGITS
    cdf
    0.08
     probability
    0.08
    æģIJ
    0.07
    byname
    0.07
     premier
    0.07
     simbol
    0.07
    Ctr
    0.06
    èĩĢ
    0.06
     Probability
    0.06
    xcb
    0.06
    Activations Density 0.001%

    No Known Activations