© 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. 61483
    Prev
    Next
    INDEX
    Explanations

    function calls with arguments

    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
    ugo
    -0.07
    heimer
    -0.06
    shall
    -0.06
    æ¶ī
    -0.06
    P
    -0.06
    è¿Ļæł·ä¸Ģ个
    -0.06
    家å®Ŀ
    -0.06
    å¿¿
    -0.06
     Lub
    -0.06
    _evt
    -0.06
    POSITIVE LOGITS
    å±
    0.08
    almaz
    0.08
    REA
    0.08
    æ¿Ģ
    0.08
    移
    0.08
    atoi
    0.07
    ensif
    0.07
    ursa
    0.07
    jong
    0.07
    utar
    0.07
    Activations Density 0.015%

    No Known Activations