© 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. 15047
    Prev
    Next
    INDEX
    Explanations

    direction and coordinate changes

    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
     Ñįкзем
    -0.07
    èĬ¹
    -0.07
    天éªĦ
    -0.06
    cev
    -0.06
    ä¸ĩçī©
    -0.06
    PLE
    -0.06
    é£İæł¼åĴĮ
    -0.06
    æ²¹æĿ¡
    -0.06
    вакÑĥ
    -0.06
    ,proto
    -0.06
    POSITIVE LOGITS
    adients
    0.08
    sbin
    0.08
    çļĦ移åĬ¨
    0.07
    å¢ŀéĩı
    0.07
    upil
    0.07
    templates
    0.07
    çļĦæĸ¹åIJij
    0.07
    aginator
    0.07
    移åĬ¨
    0.07
    移åĭķ
    0.07
    Activations Density 0.005%

    No Known Activations