© 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. 29624
    Prev
    Next
    INDEX
    Explanations

    pattern inspection and recognition

    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
    ä¸Ģ空
    -0.08
     fleste
    -0.08
    eration
    -0.08
    rada
    -0.08
    idas
    -0.08
    ë§ĪìŀIJ
    -0.08
    åĴĮ西
    -0.08
    istrator
    -0.08
    abeth
    -0.08
    itative
    -0.07
    POSITIVE LOGITS
    åı¯å¾ª
    0.09
    heus
    0.08
    ed
    0.08
     halinde
    0.08
    mÃ¤ÃŁ
    0.08
    à¸ģารà¸ĵà¹Į
    0.08
    etically
    0.07
    ahal
    0.07
    uches
    0.07
    oenix
    0.07
    Activations Density 0.030%

    No Known Activations