© 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. 17841
    Prev
    Next
    INDEX
    Explanations

    JSON or code structure delimiters

    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
    å¼ĤåŁŁ
    -0.08
    tvr
    -0.08
    bery
    -0.07
    Undefined
    -0.07
    ä¸įäºī
    -0.07
    ocab
    -0.07
    boli
    -0.07
    ÑģлÑı
    -0.07
    ä¸įè´¥
    -0.07
    OLUTE
    -0.07
    POSITIVE LOGITS
    ipper
    0.09
    åľĪåľĪ
    0.07
    udy
    0.07
    wang
    0.07
     اÙĦØ¥Ùħ
    0.07
    nal
    0.07
    asser
    0.07
    åľº
    0.06
    VN
    0.06
    нк
    0.06
    Activations Density 0.001%

    No Known Activations