© 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. 58199
    Prev
    Next
    INDEX
    Explanations

    Kochanowski, Ka, Pedy, uterrudite

    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
    æĬī
    -0.07
    inal
    -0.07
    /*
    -0.06
    quel
    -0.06
    efa
    -0.06
    ÙĪÙĨØ©
    -0.06
    atures
    -0.06
    utral
    -0.06
    åľ°æľĽçĿĢ
    -0.06
    pta
    -0.06
    POSITIVE LOGITS
    !’
    0.07
    :"-
    0.07
     **‘
    0.07
    ovski
    0.07
    ä¸ļåĨħ
    0.07
    ?’
    0.07
    öhe
    0.07
    æĻĵ彤
    0.07
    icrosoft
    0.07
    æĢ»éĩıçļĦ
    0.06
    Activations Density 0.349%

    No Known Activations