© 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. 46997
    Prev
    Next
    INDEX
    Explanations

    Modern treatment era

    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
    mend
    -0.07
    èĦĤ
    -0.07
    åıªä»£è¡¨
    -0.07
    wat
    -0.07
    ç³ľ
    -0.07
    ç¨
    -0.07
    SV
    -0.07
    æѤè¡Į
    -0.07
    abox
    -0.07
     ละ
    -0.07
    POSITIVE LOGITS
     Burgos
    0.07
     ex
    0.06
    oms
    0.06
    åª
    0.06
    æĸ°å®ī
    0.06
    ä¸īåĽĽ
    0.06
    dad
    0.06
    åĽĽäºĶ
    0.06
     instant
    0.06
    lesen
    0.06
    Activations Density 0.006%

    No Known Activations