© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63957
    Prev
    Next
    INDEX
    Explanations

    physical or abstract properties

    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
    vrier
    -0.06
    èĮĹ
    -0.06
    ezer
    -0.06
    å§Ĭ妹
    -0.06
    å¿ĥæĤ¦
    -0.06
    ogh
    -0.06
    çĤ¹åIJİ
    -0.06
    åIJ¸çĿĽ
    -0.06
     ëĬIJëĤĮ
    -0.06
    endor
    -0.06
    POSITIVE LOGITS
    对åѦçĶŁçļĦ
    0.07
    对人çļĦ
    0.07
    -bearing
    0.07
    geg
    0.07
    orges
    0.07
    -related
    0.07
     yourselves
    0.07
    лÑİб
    0.07
    çľĭåľ¨çľ¼éĩĮ
    0.07
    oms
    0.07
    Activations Density 0.046%

    No Known Activations