© 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. 64821
    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
    ocities
    -0.07
    æ¬ł
    -0.06
    çī¹å°Ķ
    -0.06
    å¼Ĥ
    -0.06
    è¨Ģä¹ĭ
    -0.06
    jord
    -0.06
    à¹Ģรà¸Ļ
    -0.06
    vé
    -0.06
    alt
    -0.06
    rove
    -0.06
    POSITIVE LOGITS
    éĩįä¸Ńä¹ĭéĩį
    0.07
    缸äºĴ交æµģ
    0.06
    论åĿĽä¸Ĭ
    0.06
    ä½łä¸Ģ个
    0.06
    indir
    0.06
    è¡ĮåĬ¨æĸ¹æ¡Ī
    0.06
    azza
    0.06
    åħ¶ä¹IJ
    0.06
    éĤ±
    0.06
    ä¸ĵçıŃ
    0.06
    Activations Density 0.011%

    No Known Activations