© 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. 13978
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in texts

    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
    estan
    -0.07
    aptive
    -0.07
    пÑĢав
    -0.06
    bred
    -0.06
    rais
    -0.06
    以身
    -0.06
    ramer
    -0.06
    ุà¸ģ
    -0.06
    rens
    -0.06
    lø
    -0.06
    POSITIVE LOGITS
    UER
    0.07
    á»ı
    0.07
     fri
    0.07
    masuk
    0.07
    æŁ¥çľĭæĽ´å¤ļ
    0.07
    åŁĶ
    0.07
    å±Ĭåħ¨åĽ½
    0.07
    次éĺħ读
    0.07
    'RE
    0.06
    å°Ķåħĭ
    0.06
    Activations Density 0.185%

    No Known Activations