© 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. 8081
    Prev
    Next
    INDEX
    Explanations

    measure, look, nit, my

    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
    ida
    -0.08
    ah
    -0.07
    anga
    -0.06
    ax
    -0.06
    arm
    -0.06
    ahan
    -0.06
    ith
    -0.06
    ain
    -0.06
    aman
    -0.06
    aine
    -0.06
    POSITIVE LOGITS
    è¶ĭ
    0.08
    angkan
    0.08
    اÙĨÛĮ
    0.08
    好货
    0.07
    sic
    0.07
    egov
    0.07
    sait
    0.07
    æŶéĹ´åľ¨
    0.07
    vista
    0.07
    å§ĭèĩ³
    0.07
    Activations Density 0.324%

    No Known Activations