© 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. 12251
    Prev
    Next
    INDEX
    Explanations

    a [noun]

    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
    vios
    -0.08
    ä¿Ĺ
    -0.08
    aling
    -0.07
    èµĤ
    -0.07
    artner
    -0.07
    é¦
    -0.07
    ultas
    -0.07
    æľ¬æĬ¥
    -0.07
    ев
    -0.06
    ublica
    -0.06
    POSITIVE LOGITS
    unjuk
    0.07
    æĻĵ举
    0.07
    lak
    0.06
    æĨ²
    0.06
     Holden
    0.06
    è¿ĩç¨ĭ
    0.06
    åķĬåķĬ
    0.06
     Leading
    0.06
     ει
    0.06
     leading
    0.06
    Activations Density 0.005%

    No Known Activations