© 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. 16188
    Prev
    Next
    INDEX
    Explanations

    producing or breakdown

    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
     جاÙĩ
    -0.07
    sök
    -0.07
    è¦ģ使
    -0.07
    fax
    -0.06
    ادات
    -0.06
    hung
    -0.06
    mares
    -0.06
    ades
    -0.06
    _TRY
    -0.06
    -addons
    -0.06
    POSITIVE LOGITS
     menghasilkan
    0.16
    产çĶŁ
    0.15
    éĩĬæĶ¾åĩº
    0.15
     producing
    0.15
     yielding
    0.15
    产çĶŁäºĨ
    0.15
     produces
    0.15
    产çĶŁçļĦ
    0.14
     generates
    0.14
    ä¼ļ产çĶŁ
    0.14
    Activations Density 0.240%

    No Known Activations