© 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. 14926
    Prev
    Next
    INDEX
    Explanations

    blank

    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
    ourcem
    -0.08
    ially
    -0.08
    rano
    -0.08
    ezz
    -0.07
    åѦåĪ°äºĨå¾Īå¤ļ
    -0.07
    bole
    -0.07
    æĪijçļĦç¥Ŀç¦ı
    -0.07
    <|box_end|>
    -0.07
    ç½ijå°ıç¼ĸ
    -0.07
    -vous
    -0.07
    POSITIVE LOGITS
    erweise
    0.09
    å¤Ħ
    0.09
    ìĿĦ
    0.08
    furter
    0.08
    ed
    0.08
    ÙĬØ©
    0.08
    aroo
    0.08
    heit
    0.08
    usters
    0.08
    éĻħ
    0.08
    Activations Density 0.008%

    No Known Activations