© 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. 16702
    Prev
    Next
    INDEX
    Explanations

    believes in eternal life

    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
    arget
    -0.07
    給人
    -0.07
    ue
    -0.06
    强åĪ¶æī§è¡Į
    -0.06
    æĹłå¥ĪçļĦ
    -0.06
     berku
    -0.06
     ÑĪÑĤ
    -0.06
    adj
    -0.06
     Liberty
    -0.06
    ç´¢æĢ§
    -0.06
    POSITIVE LOGITS
    èĻĶè¯ļ
    0.10
    积累çļĦ
    0.08
     sincerely
    0.08
     committed
    0.08
     sincere
    0.08
    athon
    0.08
    ä¸Ģ念
    0.08
     diligently
    0.08
     persever
    0.07
     repent
    0.07
    Activations Density 0.033%

    No Known Activations