© 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. 4516
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific 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
    è¿ĺæľī个
    -0.08
    è¿ĺæľīä¸Ģç§į
    -0.08
    angnya
    -0.07
    iken
    -0.07
    ои
    -0.07
    è¿ĺæľīä¸Ģ个
    -0.07
    dek
    -0.07
    ÃīG
    -0.07
    ardown
    -0.07
    ang
    -0.07
    POSITIVE LOGITS
    åħĪæĺ¯
    0.08
     perhaps
    0.08
    ä¾ĭå¦Ĥ
    0.07
    æ¯Ķå¦Ĥ
    0.07
    åĪĹåĩº
    0.07
     például
    0.07
    æĹ¢çĦ¶
    0.07
     firstly
    0.07
    鼷æĸ¯
    0.06
    inidad
    0.06
    Activations Density 0.004%

    No Known Activations