© 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. 18252
    Prev
    Next
    INDEX
    Explanations

    turn, month, once

    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
    urig
    -0.07
    ä¸Ģæĸ¹çļĦ
    -0.07
     prov
    -0.07
    etra
    -0.07
    ä¸Ģæĭ³
    -0.06
    éĹª
    -0.06
     novel
    -0.06
    ä½ľçļĦ
    -0.06
    گاÙĩ
    -0.06
    .hand
    -0.06
    POSITIVE LOGITS
    Charset
    0.08
    ovski
    0.08
    :normal
    0.07
    imuth
    0.07
    åĽłåŃIJ
    0.07
    åĩĦåĩī
    0.07
    intang
    0.07
     Contributor
    0.07
    壯
    0.07
    ablement
    0.07
    Activations Density 0.002%

    No Known Activations