© 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. 50450
    Prev
    Next
    INDEX
    Explanations

    p < 0.001

    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
    chette
    -0.08
    ücü
    -0.07
    clair
    -0.07
    æĽ´å¤ļèµĦ讯
    -0.07
     shim
    -0.07
    üc
    -0.07
    ibilit
    -0.07
    iana
    -0.07
    .Messaging
    -0.07
    à§ĭধ
    -0.07
    POSITIVE LOGITS
    å©¢
    0.07
    æĹłæĤĶ
    0.07
    ัà¸ķ
    0.07
     disbelief
    0.07
    æ¶Ľ
    0.07
     recreated
    0.06
    ä¸įçŃī
    0.06
    ust
    0.06
    天å®ĩ
    0.06
    picable
    0.06
    Activations Density 0.015%

    No Known Activations