© 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. 64118
    Prev
    Next
    INDEX
    Explanations

    followed by "A:"

    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
    å¿ĺ
    -0.08
    Õ²
    -0.07
    iring
    -0.07
    нок
    -0.07
    .asc
    -0.07
    <|box_end|>
    -0.07
    udies
    -0.07
    anske
    -0.07
    imi
    -0.07
     derby
    -0.07
    POSITIVE LOGITS
     Mé
    0.07
    _estimator
    0.06
    -tw
    0.06
    FLAGS
    0.06
    æĮĤæľº
    0.06
     cé
    0.06
    <j
    0.06
    ç»ĻäºĨæĪij们
    0.06
    سÙĨ
    0.06
    à¦ķà§įর
    0.06
    Activations Density 0.032%

    No Known Activations