© 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. 34572
    Prev
    Next
    INDEX
    Explanations

    specific punctuation followed by words

    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
    irro
    -0.08
    Âł
    -0.07
    æī§
    -0.07
    ett
    -0.07
    åľ¨ä»ĬåIJİçļĦå·¥ä½ľä¸Ń
    -0.07
    illi
    -0.07
    ä¹ĻåıĮæĸ¹
    -0.06
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.06
    .tw
    -0.06
    éĴµ
    -0.06
    POSITIVE LOGITS
    ä¸Ģ个æĺ¯
    0.11
    åīįèĢħ
    0.11
    åĪĨåĪ«æĺ¯
    0.10
    é¦ĸåħĪæĺ¯
    0.10
    ä¸Ģç§įæĺ¯
    0.10
    第ä¸Ģç§į
    0.09
    ä¸Ģæĺ¯
    0.09
    第ä¸Ģ项
    0.09
     erster
    0.09
    第ä¸Ģ
    0.09
    Activations Density 0.091%

    No Known Activations