© 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. 42296
    Prev
    Next
    INDEX
    Explanations

    disabled people, North Korea, aging research, workplace policy, procurement, e-commerce, apples, labour, health, polyamines

    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
    ippy
    -0.07
    inkin
    -0.07
    ÏĢοί
    -0.07
    éĩijæĸ¯
    -0.07
    å¸ĮæľĽå¯¹æĤ¨
    -0.07
    дейÑģÑĤвие
    -0.07
    éné
    -0.07
    æĿijæĿij
    -0.06
    vÃŃ
    -0.06
    anko
    -0.06
    POSITIVE LOGITS
     каÑģ
    0.08
    è·¯ä¸Ĭ
    0.07
    uers
    0.07
    stro
    0.07
    ç®Ģ
    0.07
    GER
    0.06
    azza
    0.06
    åİ»å¤Ħ
    0.06
    ÎŃλ
    0.06
    Doc
    0.06
    Activations Density 1.164%

    No Known Activations