© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22979
    Prev
    Next
    INDEX
    Explanations

    now followed by punctuation or pronouns

    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
    åIJĮæ¯Ķåĩıå°ij
    -0.07
    éĢ
    -0.07
    /or
    -0.06
    ya
    -0.06
    æľīéģĵ
    -0.06
    åİ¿
    -0.06
    没éĶĻ
    -0.06
    imar
    -0.06
    ALLY
    -0.06
    ä½ļåIJį
    -0.06
    POSITIVE LOGITS
    วà¸ģ
    0.08
    èĩ³äºİ
    0.08
     concr
    0.08
    lad
    0.08
    åħ·ä½ĵçļĦ
    0.08
    że
    0.07
    eve
    0.07
    xic
    0.07
     ÑģобÑģÑĤвенно
    0.07
    sWith
    0.07
    Activations Density 0.003%

    No Known Activations