© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63824
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    ropa
    -0.08
    umba
    -0.07
    æ¡ijæĭ¿
    -0.07
    verbose
    -0.06
     laz
    -0.06
     cancell
    -0.06
    quit
    -0.06
    ä¸ĥåįģäºĮ
    -0.06
    minus
    -0.06
     Rut
    -0.06
    POSITIVE LOGITS
    纯粹
    0.09
    uss
    0.08
    razy
    0.08
    å°±å®ĮæĪIJäºĨ
    0.08
    å¦Ĥæ°´
    0.07
     (<
    0.07
    ä½Ĩæĺ¯è¦ģ
    0.07
    å°±èĥ½
    0.07
    á»ģm
    0.07
    /nginx
    0.07
    Activations Density 0.148%

    No Known Activations