© 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. 20698
    Prev
    Next
    INDEX
    Explanations

    medical data services

    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
     appunto
    -0.07
    arel
    -0.07
    æŬ
    -0.07
    èij©
    -0.07
    ayet
    -0.06
     guardians
    -0.06
    夫
    -0.06
     _.
    -0.05
    rid
    -0.05
    å²IJ
    -0.05
    POSITIVE LOGITS
    شت
    0.08
     ulo
    0.07
    egot
    0.07
    иÑĤаÑĢ
    0.07
     übrigens
    0.07
    严äºİ
    0.07
    ึà¸ĩ
    0.07
    .openg
    0.07
    ÃŃb
    0.07
    å¸Ĥ人æ°ijæ³ķéĻ¢
    0.07
    Activations Density 0.538%

    No Known Activations