© 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. 24820
    Prev
    Next
    INDEX
    Explanations

    sentence boundary 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
    anean
    -0.09
    umon
    -0.09
    abbo
    -0.08
    ä½ķæĸ¹
    -0.08
    undas
    -0.08
    lfw
    -0.08
    anzo
    -0.08
    aukee
    -0.08
    ardini
    -0.08
     kalkul
    -0.08
    POSITIVE LOGITS
    ↵
    0.07
     other
    0.07
    该æľīçļĦ
    0.06
     importantly
    0.06
     crucial
    0.06
     ad
    0.06
    çļĦåħ¶ä»ĸ
    0.06
    æ¯ĶæĪij
    0.06
    oss
    0.06
    丽åįİ
    0.06
    Activations Density 0.002%

    No Known Activations