© 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. 3251
    Prev
    Next
    INDEX
    Explanations

    qualification or explanation

    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
    èµŀè¿ĩ
    -0.07
     vara
    -0.07
    èĻ½çĦ¶ä¸įæĺ¯
    -0.06
    æĥ³äºĨ解
    -0.06
    äºĨä¸įèµ·
    -0.06
    обÑĭ
    -0.06
    ding
    -0.06
    aset
    -0.06
    BUFF
    -0.06
    ä¸įäºĨçļĦ
    -0.06
    POSITIVE LOGITS
    yel
    0.08
    éĶħçĽĸ
    0.08
    æŶåĪ»ä¿ĿæĮģ
    0.07
    Ñıви
    0.07
     Taip
    0.07
    ibir
    0.07
    翼翼
    0.07
    _NUMERIC
    0.07
    hausen
    0.07
     palate
    0.07
    Activations Density 0.003%

    No Known Activations