© 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. 64651
    Prev
    Next
    INDEX
    Explanations

    carcinomas, occupant, kingdom, older adult

    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
    jÅ¡ÃŃ
    -0.07
    让åIJĮåѦ们
    -0.07
    åģļå¾ĹæĽ´å¥½
    -0.07
     \/
    -0.07
    éĤ£è¾¹çļĦ
    -0.07
    èĻ½çĦ¶ä¸įæĺ¯
    -0.06
    å¤©æ±ł
    -0.06
    evas
    -0.06
    аÑĤе
    -0.06
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.06
    POSITIVE LOGITS
    åĨħ容æıIJä¾Ľæĸ¹
    0.08
    èĨĢ
    0.07
    ç®Ģ称
    0.07
    à¸Ľà¸²
    0.07
    以å°ı
    0.07
    isk
    0.07
    apun
    0.07
    çĥŁéĽ¨
    0.06
    ending
    0.06
    olut
    0.06
    Activations Density 0.067%

    No Known Activations