© 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. 64899
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    à¸Ķ
    -0.07
    izie
    -0.07
    ä¸ºæľŁ
    -0.07
     ï¿¥
    -0.07
    âĢ¦ãĢĤ
    -0.07
    ritos
    -0.07
    iales
    -0.06
    .addEventListener
    -0.06
    orte
    -0.06
    chs
    -0.06
    POSITIVE LOGITS
    øy
    0.07
    ingly
    0.07
    butt
    0.07
    ogg
    0.07
    ally
    0.07
    æĶ¾çŁ¢
    0.07
    èĮĥæĸĩç½ij
    0.07
    åł¡
    0.06
    sic
    0.06
    akis
    0.06
    Activations Density 1.219%

    No Known Activations