© 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. 28059
    Prev
    Next
    INDEX
    Explanations

    numbers and table separators

    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
    夺
    -0.07
    ä¸įåĥı
    -0.06
    é¦
    -0.06
    ä»ĺ诸
    -0.06
    incinn
    -0.06
    åģļå®ŀ
    -0.06
    é¦į
    -0.06
     hale
    -0.06
    çĥŃæĴŃ
    -0.06
    fo
    -0.06
    POSITIVE LOGITS
    å°ĶèĴĻ
    0.08
    _legend
    0.08
    abez
    0.08
    INDER
    0.08
    æľīéģĵ
    0.08
     dén
    0.08
    ัม
    0.07
    anus
    0.07
    erosis
    0.07
     hers
    0.07
    Activations Density 0.001%

    No Known Activations