© 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. 33423
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    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
    黼
    -0.07
    à¸ļà¹īาà¸ĩ
    -0.07
     intentionally
    -0.06
    acol
    -0.06
    igrations
    -0.06
    -ahead
    -0.06
    inkel
    -0.06
     apro
    -0.06
    retty
    -0.06
     Buffered
    -0.06
    POSITIVE LOGITS
    ç¥ĽéĻ¤
    0.11
    æºIJ头
    0.10
     identified
    0.10
    æ¸ħéĻ¤
    0.10
    åİ»éĻ¤
    0.09
    /remove
    0.09
     offending
    0.09
    çĹħåĽł
    0.09
     removal
    0.09
    æ¶ĪéĻ¤
    0.09
    Activations Density 0.170%

    No Known Activations