© 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. 33831
    Prev
    Next
    INDEX
    Explanations

    action verbs and commands

    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
    yarat
    -0.09
    amo
    -0.08
    embl
    -0.08
     nodig
    -0.08
    CanBe
    -0.08
    çĶ¨å®ĥ
    -0.07
    tanda
    -0.07
    ÑĬÑĤ
    -0.07
    lah
    -0.07
    ariah
    -0.07
    POSITIVE LOGITS
     ×ķ׾×Ķ
    0.14
     oneself
    0.12
    ain
    0.09
    åĴĮå®ŀæĸ½
    0.08
    åĵªæĢķ
    0.08
     ÑģамомÑĥ
    0.07
     ×ķ׾
    0.07
    åĴĮä¿ĿæĬ¤
    0.07
    åĴĮæĶ¹åĸĦ
    0.07
    /not
    0.07
    Activations Density 0.894%

    No Known Activations