© 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. 46078
    Prev
    Next
    INDEX
    Explanations

    software libraries and technical terms

    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°ijæľīçļĦ
    -0.07
    ÑĢоб
    -0.07
     fasta
    -0.06
    使ä¹ĭ
    -0.06
    泡
    -0.06
    sortable
    -0.06
     admittedly
    -0.06
     teatra
    -0.06
    rab
    -0.06
    processable
    -0.06
    POSITIVE LOGITS
    åŃ¦ä¹łæķĻèĤ²
    0.07
    ç¼Ī
    0.07
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.07
    ä¹ĭåĽ½
    0.07
    :\"
    0.07
    åĵ²
    0.06
    ä¼ļè®®çĶ±
    0.06
     Tant
    0.06
     âĢİ
    0.06
    anyi
    0.06
    Activations Density 0.002%

    No Known Activations