© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64070
    Prev
    Next
    INDEX
    Explanations

    choices, first, red, vote, card

    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
    abis
    -0.08
    ubin
    -0.07
    åıĮ缮
    -0.07
    intang
    -0.07
     thereof
    -0.07
    umin
    -0.07
    æ¢Ń
    -0.06
    å©Ĩ
    -0.06
     saturated
    -0.06
    IDER
    -0.06
    POSITIVE LOGITS
    ä¹±
    0.09
     random
    0.08
     randomly
    0.08
    _FIXED
    0.08
    egue
    0.08
    random
    0.07
    éļıæľº
    0.07
    äºĤ
    0.07
    Choices
    0.07
    .getMethod
    0.07
    Activations Density 0.001%

    No Known Activations