© 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. 29732
    Prev
    Next
    INDEX
    Explanations

    article number

    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
    æķĻèĤ²ç½ij
    -0.09
    çľģå§Ķ常å§Ķ
    -0.09
    uelas
    -0.08
    ENU
    -0.08
    åİ¿æķĻèĤ²å±Ģ
    -0.08
     evacu
    -0.08
    cuit
    -0.08
    ï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭ
    -0.08
     konser
    -0.08
    å¸ĤæķĻèĤ²å±Ģ
    -0.08
    POSITIVE LOGITS
     doi
    0.09
     pp
    0.08
     J
    0.08
     DOI
    0.08
    doi
    0.08
    åĭĺ
    0.07
     ISSN
    0.07
     peer
    0.07
     pub
    0.07
     article
    0.07
    Activations Density 0.285%

    No Known Activations