© 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. 12126
    Prev
    Next
    INDEX
    Explanations

    autosomal dominant or recessive inheritance

    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
    éĤĥ
    -0.09
    essin
    -0.08
    occhi
    -0.08
    驹
    -0.08
    ìĨĮë¹Ħ
    -0.08
    -archive
    -0.08
     láng
    -0.08
    evin
    -0.08
    lew
    -0.08
    elius
    -0.08
    POSITIVE LOGITS
    ä¼łæĿ¥
    0.07
     inheritance
    0.06
    recht
    0.06
     trait
    0.06
     non
    0.06
     common
    0.06
    ä¸įçĶ±
    0.06
     Advert
    0.06
     progressive
    0.06
    ä¸ĬçļĦ
    0.06
    Activations Density 0.012%

    No Known Activations