© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41595
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    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
    staking
    -0.08
     Setia
    -0.08
    isman
    -0.08
    achs
    -0.08
    åħ³å¿ĥåĴĮ
    -0.08
    leurs
    -0.07
    воÑĢ
    -0.07
    urras
    -0.07
    fur
    -0.07
    äºĭåıij
    -0.07
    POSITIVE LOGITS
    less
    0.07
     shim
    0.07
    hip
    0.06
    zcz
    0.06
    azon
    0.06
    sstr
    0.06
     indirectly
    0.06
    LESS
    0.06
    lessly
    0.06
    èµĸ
    0.06
    Activations Density 0.472%

    No Known Activations