© 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. 55450
    Prev
    Next
    INDEX
    Explanations

    .h, .lo, .o, .js file suffixes

    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
    æľªç»ı
    -0.07
    Assembler
    -0.07
    æĽ´ä¸įè¦ģ
    -0.07
    üng
    -0.06
    onical
    -0.06
    ervo
    -0.06
    ë¦Ħ
    -0.06
    Href
    -0.06
    INGTON
    -0.06
    зд
    -0.06
    POSITIVE LOGITS
    宿
    0.09
    leter
    0.08
    å¤ļåĽ¾
    0.08
    âĸ·
    0.07
    _BP
    0.07
    æĶ¶
    0.07
    stalk
    0.07
    ighb
    0.07
    beh
    0.07
    ategies
    0.07
    Activations Density 0.286%

    No Known Activations