© 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. 30303
    Prev
    Next
    INDEX
    Explanations

    medical journals, research, and health areas

    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
    udet
    -0.09
    edel
    -0.07
    klen
    -0.07
    ODE
    -0.07
     Mans
    -0.07
     excer
    -0.07
    faat
    -0.07
    bsub
    -0.07
    enty
    -0.07
    ÑĦелÑĮ
    -0.07
    POSITIVE LOGITS
    oss
    0.07
    æł¸å¿ĥä»·åĢ¼è§Ĥ
    0.07
    claim
    0.07
    ä¸ĭåıijçļĦ
    0.06
     Claim
    0.06
    uson
    0.06
    åİŁåĪĻä¸Ĭ
    0.06
    eli
    0.06
    åĩĨåħ¥
    0.06
    orse
    0.06
    Activations Density 0.008%

    No Known Activations