© 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. 61927
    Prev
    Next
    INDEX
    Explanations

    medical 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
    jured
    -0.08
    евна
    -0.08
    ongyang
    -0.08
    رÙĬÙĤÙĬ
    -0.08
    ernel
    -0.08
    <|box_end|>
    -0.08
    ienio
    -0.08
    æī¬æī¬
    -0.08
    elj
    -0.07
    ieszcz
    -0.07
    POSITIVE LOGITS
    é
    0.09
    uch
    0.07
    stalk
    0.07
    abar
    0.06
    çĥ½
    0.06
    ito
    0.06
    çıŃ
    0.06
    unter
    0.06
    å«Į
    0.06
    rg
    0.06
    Activations Density 2.974%

    No Known Activations