© 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. 23318
    Prev
    Next
    INDEX
    Explanations

    html attributes

    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
    ież
    -0.07
    ayat
    -0.07
    å¸Ĥæĸ°
    -0.07
    iante
    -0.07
    ãĥ¼ãĤ¿
    -0.07
    Äħtek
    -0.07
    NDER
    -0.07
    å°Ŀ
    -0.06
    atab
    -0.06
    senz
    -0.06
    POSITIVE LOGITS
    çİĩçļĦ
    0.06
    ئ
    0.06
    ustain
    0.06
    åįij
    0.06
    just
    0.06
    è¿ľæľŁ
    0.06
    bic
    0.06
    âĢĮ
    0.06
    ÏĢί
    0.06
    ÏĨή
    0.06
    Activations Density 0.077%

    No Known Activations