© 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. 21505
    Prev
    Next
    INDEX
    Explanations

    headgear and coverings

    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
    ç³ľ
    -0.09
    qrt
    -0.08
    ignum
    -0.08
    粪便
    -0.07
    åIJĪåIJĮå±¥è¡Į
    -0.07
     UIControl
    -0.07
    åİķ
    -0.07
    ளà¯įள
    -0.07
    åIJĪåIJĮ
    -0.07
    å±¥è¡ĮçļĦ
    -0.07
    POSITIVE LOGITS
    /head
    0.17
    é¢ħ
    0.14
    -head
    0.13
    éłŃ
    0.13
     head
    0.13
    头çļĦ
    0.12
    çĽĶ
    0.12
    (head
    0.12
    头éĥ¨
    0.12
    æŀķ
    0.12
    Activations Density 0.161%

    No Known Activations