© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7223
    Prev
    Next
    INDEX
    Explanations

    ADHD and autism struggles

    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
    icina
    -0.08
    åħ¶æīĢ
    -0.07
    æģĨ
    -0.07
    -proxy
    -0.07
    jenigen
    -0.07
    ograd
    -0.07
    еÑĪе
    -0.07
    Obsolete
    -0.07
    ünsch
    -0.07
     doubl
    -0.07
    POSITIVE LOGITS
    /OR
    0.08
    czo
    0.07
    isd
    0.07
    chk
    0.07
    sg
    0.07
    ream
    0.06
    æľĢå¤ļçļĦ
    0.06
    EventData
    0.06
    ison
    0.06
     xÃŃ
    0.06
    Activations Density 0.001%

    No Known Activations