© 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. 62373
    Prev
    Next
    INDEX
    Explanations

    study start indicators

    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
    Whats
    -0.08
    å¹
    -0.07
    åIJĪ
    -0.07
     fing
    -0.07
    åīįåIJİ
    -0.07
    äºŃ
    -0.06
    enery
    -0.06
    ắt
    -0.06
    _SU
    -0.06
    ç§ĭæľĪ
    -0.06
    POSITIVE LOGITS
    人åķĬ
    0.08
    |R
    0.07
    lus
    0.07
    olta
    0.07
    leigh
    0.07
    ืà¹īà¸Ļ
    0.07
    質
    0.07
    رÙĪج
    0.07
    igos
    0.07
    æľīçĶŁ
    0.07
    Activations Density 0.001%

    No Known Activations