© 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. 41398
    Prev
    Next
    INDEX
    Explanations

    rehearing or decided

    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
    aint
    -0.07
    -0.06
     Near
    -0.06
    æ©Ħ
    -0.06
    -0.06
     \
    -0.06
    ẹ
    -0.06
    ÙİÙijÙĩÙı
    -0.06
    å·¾
    -0.06
    near
    -0.06
    POSITIVE LOGITS
    alkan
    0.08
    AXB
    0.07
    alk
    0.07
    hil
    0.07
    ĥģ
    0.07
    èĭ¥æĺ¯
    0.07
    uzz
    0.07
    ë¿Į
    0.07
    -Sah
    0.07
     diff
    0.07
    Activations Density 0.015%

    No Known Activations