© 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. 7653
    Prev
    Next
    INDEX
    Explanations

    code assignment operators

    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
    è¿ĺæľīä¸ĢçĤ¹
    -0.08
    assi
    -0.07
    åĿŀ
    -0.07
    à¸ķุ
    -0.07
    é£
    -0.07
    å«ģ
    -0.07
    åºIJ
    -0.07
    ỳnh
    -0.07
    è¿ĺæľīçĤ¹
    -0.07
    ئÙĬÙĨ
    -0.07
    POSITIVE LOGITS
    çIJĨ
    0.08
    ;break
    0.07
    çĽ¸ä¼¼æĸĩçĮ®
    0.07
    æŁĵ
    0.07
    "]}
    0.06
     tÄĥm
    0.06
    ç¦ıçĶ°
    0.06
    æIJľ
    0.06
    erable
    0.06
    èģļ
    0.06
    Activations Density 0.032%

    No Known Activations