© 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. 24214
    Prev
    Next
    INDEX
    Explanations

    items added to lists or databases

    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
    ç½ijç«Ļ导èĪª
    -0.06
    гоÑĢа
    -0.06
    keys
    -0.06
    ihal
    -0.06
     liqu
    -0.06
    æĻĵ
    -0.06
    enu
    -0.06
    errat
    -0.06
    æľ¬çĿĢ
    -0.06
    ÑĨион
    -0.06
    POSITIVE LOGITS
    iliz
    0.08
    æ·»åĬłåĪ°
    0.08
     конÑĨ
    0.07
    ebro
    0.07
    riz
    0.07
    olars
    0.07
    _DICT
    0.07
    zata
    0.07
    Å¡a
    0.07
    erta
    0.07
    Activations Density 0.001%

    No Known Activations