© 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. 23029
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by word start

    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
    éĿĸ
    -0.07
     ($(
    -0.06
     (...
    -0.06
    转载请
    -0.06
     EITHER
    -0.06
    éĢļè¿ĩ使çĶ¨
    -0.06
    pref
    -0.06
    è¬
    -0.06
    娶
    -0.06
    ilier
    -0.06
    POSITIVE LOGITS
    æĹłæīĢè°ĵ
    0.07
    åĵįå½»
    0.07
    stagram
    0.07
    åħĪåĪ°åħĪå¾Ĺ
    0.07
    ashian
    0.07
    icile
    0.07
    åİĭåĬĽå¤§
    0.07
     donc
    0.07
     alasti
    0.07
    icum
    0.07
    Activations Density 0.009%

    No Known Activations