© 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. 43813
    Prev
    Next
    INDEX
    Explanations

    depressive symptoms

    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
    udz
    -0.08
     Ø£ÙĪÙĦا
    -0.07
     tercero
    -0.07
    udou
    -0.07
    ÙĪسÙģ
    -0.07
    ohl
    -0.07
     ingy
    -0.07
    _SID
    -0.07
    _cmp
    -0.07
    ä¸ŃåĽ½çī¹èī²
    -0.07
    POSITIVE LOGITS
     calculated
    0.07
    itul
    0.06
    retty
    0.06
    imine
    0.06
    æĺ¯å¤ļå°ij
    0.06
    ä¸Ĭ涨äºĨ
    0.06
    IVEN
    0.06
    pery
    0.06
    v
    0.06
    itÃł
    0.05
    Activations Density 0.011%

    No Known Activations