© 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. 11217
    Prev
    Next
    INDEX
    Explanations

    good or effective 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
    ç«£
    -0.08
    ZER
    -0.08
    BASE
    -0.08
     kiêng
    -0.07
    keley
    -0.07
    eda
    -0.07
    strup
    -0.07
    <dd
    -0.07
    ames
    -0.07
    .Lookup
    -0.07
    POSITIVE LOGITS
    åį´æĹłæ³ķ
    0.13
    åį´è¢«
    0.12
     pourtant
    0.12
    çIJĨåºĶ
    0.11
    æĺİæĺİ
    0.11
    åį´åĽłä¸º
    0.11
    åį´ä¸įèĥ½
    0.11
    ãģªãģ®ãģ«
    0.10
    åı¯æĥľ
    0.10
    åį´
    0.10
    Activations Density 0.311%

    No Known Activations