© 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. 7808
    Prev
    Next
    INDEX
    Explanations

    sentences ending in punctuation

    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
     Afinal
    -0.08
    æľīæŶä¼ļ
    -0.08
    ä¸Ģåij³
    -0.08
    ecken
    -0.08
    并ä¸į代表
    -0.08
    æĢ»æĺ¯ä¼ļ
    -0.08
    avis
    -0.07
    ambre
    -0.07
    egg
    -0.07
    好åѦçĶŁ
    -0.07
    POSITIVE LOGITS
    ä¹ĭå¤ļ
    0.11
     (!
    0.09
    è¿ľè¶ħ
    0.08
    åIJįåī¯åħ¶å®ŀçļĦ
    0.08
    ä»ħ次äºİ
    0.07
    !!!
    0.07
    (!
    0.07
    à¹Ģลยà¸Ĺีà¹Ģà¸Ķียว
    0.07
    ä¹ĭéģ¥
    0.07
     staggering
    0.07
    Activations Density 0.547%

    No Known Activations