© 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. 29940
    Prev
    Next
    INDEX
    Explanations

    beginners, novice, newbie

    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
    aly
    -0.07
    ä¸İä¼Ĺ
    -0.07
    ÙħاÙħ
    -0.06
    alo
    -0.06
    åĽŀèį¡
    -0.06
    éļıå¿ĥ
    -0.06
    追ä¸Ĭ
    -0.06
    ä¸ĸ
    -0.06
    watan
    -0.06
     awaited
    -0.06
    POSITIVE LOGITS
    åħ¥éŨ
    0.09
    ä¹į
    0.09
    容æĺĵ产çĶŁ
    0.09
     sekalipun
    0.09
    åħ¥éĸĢ
    0.09
     assoluto
    0.09
    bies
    0.08
    ç»ıéªĮçļĦ
    0.08
     alike
    0.08
    inste
    0.08
    Activations Density 0.142%

    No Known Activations