© 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. 38486
    Prev
    Next
    INDEX
    Explanations

    suicide and suicidal behavior

    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
     impe
    -0.08
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļà¸ģาร
    -0.08
    icast
    -0.07
    åı±
    -0.07
    ycastle
    -0.07
    åIJĨ
    -0.07
    ÑĦÑĥ
    -0.07
    issance
    -0.07
    æĻ®éĢļä¼ļåijĺ
    -0.07
     businessmen
    -0.07
    POSITIVE LOGITS
     suicidal
    0.15
    èĩªæ®º
    0.14
     suicide
    0.14
     suic
    0.13
     Suicide
    0.12
     depressive
    0.10
     depression
    0.09
     suicides
    0.09
    -su
    0.09
    entic
    0.09
    Activations Density 0.042%

    No Known Activations