© 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. 26260
    Prev
    Next
    INDEX
    Explanations

    function definition

    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
    itie
    -0.08
    éļĻ
    -0.07
    [Test
    -0.07
    çľ¼çķĮ
    -0.07
    tics
    -0.07
    ables
    -0.06
     Watt
    -0.06
     вовÑģе
    -0.06
    æľīä¸Ģ段
    -0.06
    èľľæ¡ĥ
    -0.06
    POSITIVE LOGITS
    tons
    0.08
    æľ¬ç«Ļ
    0.07
    çĶµèĦijçīĪ
    0.07
    ä¼ĺåĬ£
    0.07
    nger
    0.07
    PPER
    0.07
    ä¸Ĭä¸Ģç¯ĩ
    0.07
     nháºŃn
    0.06
    å°¼äºļ
    0.06
    SEE
    0.06
    Activations Density 0.001%

    No Known Activations