© 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. 45704
    Prev
    Next
    INDEX
    Explanations

    sentence-ending 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
    Ø´ÛĮÙĨ
    -0.08
     apologise
    -0.08
    纽
    -0.08
    atriz
    -0.08
     yourselves
    -0.07
    ä¸Ģ寸
    -0.07
     absor
    -0.07
    æĴ°
    -0.07
     kép
    -0.07
     azért
    -0.07
    POSITIVE LOGITS
    acon
    0.08
    ä»ĸ们è¿ĺ
    0.07
    ensk
    0.07
    æ»´æ°´
    0.07
     Holden
    0.06
    èĢģ人家
    0.06
    nel
    0.06
    ä»ĸ认为
    0.06
    åı·ä¸º
    0.06
    asher
    0.06
    Activations Density 0.614%

    No Known Activations