© 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. 27798
    Prev
    Next
    INDEX
    Explanations

    exponents and fractions

    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
    ä¸ī两
    -0.07
    å½ĵæĻļ
    -0.07
    oon
    -0.06
    eley
    -0.06
    junto
    -0.06
    uru
    -0.06
    ovo
    -0.06
    .getState
    -0.06
    强åĬĽ
    -0.06
    üy
    -0.06
    POSITIVE LOGITS
    erness
    0.08
    çļĦä»Ĭ天
    0.07
    à¸ĸม
    0.07
    isar
    0.07
    sher
    0.07
     isize
    0.07
    æĬĬèĩªå·±
    0.07
    äºij天
    0.07
    à°Ĺà°¾
    0.07
    itelist
    0.07
    Activations Density 0.022%

    No Known Activations