© 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. 44042
    Prev
    Next
    INDEX
    Explanations

    already announced

    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
    isan
    -0.07
    echt
    -0.07
    chtig
    -0.07
    ukah
    -0.07
    çļĵ
    -0.07
    udu
    -0.07
    hp
    -0.07
    _SECOND
    -0.06
    eger
    -0.06
    åĽŀè´Ń
    -0.06
    POSITIVE LOGITS
    æĹ©å·²
    0.10
     already
    0.09
    already
    0.09
    å·²æľīçļĦ
    0.09
    çŃīåħ¶ä»ĸ
    0.09
    à¸Ńยูà¹Īà¹ģลà¹īว
    0.09
    åı¦ä¸Ģ
    0.08
     ebenfalls
    0.08
    ä¸įè¨ĢèĢĮåĸ»
    0.08
    æĹ©åīį
    0.08
    Activations Density 0.065%

    No Known Activations