© 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. 34250
    Prev
    Next
    INDEX
    Explanations

    or another

    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
    orges
    -0.09
    翻天
    -0.08
    olis
    -0.08
    essen
    -0.07
    chini
    -0.07
    ³³³³³³³³
    -0.07
    forsk
    -0.07
    otra
    -0.07
    agma
    -0.07
    itere
    -0.07
    POSITIVE LOGITS
    rent
    0.07
    æĶ¾ä¸ĭäºĨ
    0.06
    ingle
    0.06
    ET
    0.06
    et
    0.06
     continents
    0.06
     sada
    0.06
    ence
    0.06
    x
    0.06
    æIJIJ
    0.06
    Activations Density 0.004%

    No Known Activations