© 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. 20070
    Prev
    Next
    INDEX
    Explanations

    exacerbation or relapse

    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
    æĽ¿ä»£åĵģ
    -0.08
    ä¹ĭçĪ¶
    -0.08
    ../../../
    -0.08
    ali
    -0.08
    alian
    -0.08
    Clickable
    -0.08
    ÙĪÙĦÙĬ
    -0.08
    ikker
    -0.08
    erable
    -0.07
    aben
    -0.07
    POSITIVE LOGITS
    æģ¶åĮĸ
    0.11
    çĹħæĥħ
    0.10
     worsening
    0.09
    åĬ¿å¤´
    0.09
     recurrence
    0.09
     severity
    0.09
     episodes
    0.08
    åıijä½ľ
    0.08
     symptoms
    0.08
     flare
    0.08
    Activations Density 0.181%

    No Known Activations