© 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. 24137
    Prev
    Next
    INDEX
    Explanations

    function and method names

    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
    à¸ķร
    -0.07
    èĽ
    -0.07
    è¯ħ
    -0.07
    è¿ĶåĽŀ顶éĥ¨
    -0.07
    è¶ĭ
    -0.07
    ä¸įæĥĬ
    -0.06
    .har
    -0.06
    åºĩ
    -0.06
    侶
    -0.06
    ockey
    -0.06
    POSITIVE LOGITS
    ','',
    0.07
    åIJįåŁİ
    0.07
    èĢģç¥ĸ
    0.07
    ovac
    0.07
    å¿ĥ仪
    0.07
     repeatedly
    0.07
    ä¹ĭæŃĮ
    0.06
    tee
    0.06
    ométr
    0.06
    ][-
    0.06
    Activations Density 0.013%

    No Known Activations