© 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. 55522
    Prev
    Next
    INDEX
    Explanations

    well as

    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
    Ø©
    -0.10
    yclopedia
    -0.10
    evi
    -0.09
    orners
    -0.09
    es
    -0.09
    ÑģÑı
    -0.08
    áĥĺáĥł
    -0.07
    说äºĨç®Ĺ
    -0.07
    ython
    -0.07
    ฤษ
    -0.07
    POSITIVE LOGITS
    ÑĢон
    0.09
    /or
    0.09
    so
    0.08
    دة
    0.08
    ror
    0.08
     halnya
    0.08
    å¾Ĺä¸Ĭ
    0.08
    erson
    0.07
    ounded
    0.07
    ows
    0.07
    Activations Density 0.036%

    No Known Activations