© 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. 39387
    Prev
    Next
    INDEX
    Explanations

    phrases 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
    zec
    -0.07
    èĬĤèĬĤ
    -0.07
    è¿ĺæľīåĵªäºĽ
    -0.06
    opa
    -0.06
    ä¸Ĭ人
    -0.06
     autoload
    -0.06
    ysh
    -0.06
    è¿ĶåĽŀåĪĹ表
    -0.06
    足äºĨ
    -0.06
    orza
    -0.06
    POSITIVE LOGITS
    ä¸įæ¯Ķ
    0.08
    bid
    0.08
    пеÑĢвÑĭе
    0.07
    åİŁåĪĻä¸Ĭ
    0.07
    ä¸ĢèĪ¬æĥħåĨµä¸ĭ
    0.07
    å·¥ä½ľæŶ
    0.07
    ','.
    0.07
    æīĢæľīçļĦ
    0.07
    ä¸ĢèĪ¬èĢĮè¨Ģ
    0.07
    ãģŁãģłãģĹ
    0.07
    Activations Density 0.875%

    No Known Activations