© 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. 41086
    Prev
    Next
    INDEX
    Explanations

    In context of descriptions

    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
    arat
    -0.07
    éĵ¡
    -0.07
    ä¸Ĭéĥ½
    -0.07
    mgr
    -0.07
    æľºåŀĭ
    -0.06
    å§
    -0.06
    转载èĩ³
    -0.06
    otella
    -0.06
    ä¸ĬåĬł
    -0.06
    ãĥ«ãĤ¯
    -0.06
    POSITIVE LOGITS
    ......
    0.08
    ........
    0.07
    .......
    0.07
    /background
    0.07
    .........
    0.07
     .....
    0.07
     vie
    0.07
    egis
    0.07
    utor
    0.07
    âĢ¦âĢ¦ãĢĤ
    0.07
    Activations Density 0.005%

    No Known Activations