© 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. 18766
    Prev
    Next
    INDEX
    Explanations

    breast cancer

    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
    aus
    -0.07
    itty
    -0.07
    ipun
    -0.07
    åħĭç½Ĺåľ°äºļ
    -0.06
    ock
    -0.06
    onym
    -0.06
    rawer
    -0.06
    åľ¨å»º
    -0.06
    iman
    -0.06
    ité
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸Ģéģĵ
    0.07
    UES
    0.07
    riages
    0.07
    าà¸Ħม
    0.07
    LEX
    0.07
    永康
    0.07
    ysteme
    0.06
    arbon
    0.06
    æĥ³å¾Ĺ
    0.06
    符
    0.06
    Activations Density 0.662%

    No Known Activations