© 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. 18222
    Prev
    Next
    INDEX
    Explanations

    Major Depressive Disorder

    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
    Âł
    -0.08
    ipple
    -0.07
     others
    -0.07
    гази
    -0.06
    ³³
    -0.06
    æĪijå½ĵæŶ
    -0.06
    çľ·
    -0.06
    PCS
    -0.06
    ç¬ijåĤ²
    -0.06
    çĤ¹è¿ĻéĩĮ
    -0.06
    POSITIVE LOGITS
    iard
    0.08
    lep
    0.08
    carlo
    0.07
    ầm
    0.07
    æľ¬å¸ĸ
    0.07
     olaraq
    0.07
     dietro
    0.07
    ogl
    0.07
    witz
    0.07
    mir
    0.07
    Activations Density 0.001%

    No Known Activations