© 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. 20293
    Prev
    Next
    INDEX
    Explanations

    of chronic conditions

    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
    incer
    -0.08
    am
    -0.07
    inn
    -0.07
    oy
    -0.07
    å°ıéĻ¢
    -0.07
    vious
    -0.06
    ysterious
    -0.06
    æºIJæĢ§
    -0.06
    ara
    -0.06
    amb
    -0.06
    POSITIVE LOGITS
     sorts
    0.07
    ëıĪ
    0.07
    /of
    0.07
    keln
    0.07
    åį³åľ¨
    0.07
    kke
    0.06
    å¦Ĥåľ¨
    0.06
    iants
    0.06
    iative
    0.06
    dera
    0.06
    Activations Density 0.735%

    No Known Activations