© 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. 16110
    Prev
    Next
    INDEX
    Explanations

    type i error rate

    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
    ainter
    -0.08
    èµĦ产交æĺĵ
    -0.07
    å¡ĺéķĩ
    -0.07
    ä¹ĭéĹ´çļĦæĦŁæĥħ
    -0.07
    请åıĬæŶä¸İæĪij们èģĶç³»
    -0.07
    zio
    -0.07
     fér
    -0.07
    ãĥ¯ãĤ¯ãĥģãĥ³
    -0.07
    .motion
    -0.07
     Massive
    -0.07
    POSITIVE LOGITS
    edly
    0.08
    æ¸Ĭ
    0.07
    åĪĢåŃIJ
    0.07
     Toolbox
    0.07
    çļĦåIJįä¹ī
    0.07
    åIJī祥å¦ĤæĦı
    0.07
    çļĦ羣
    0.07
    æľĢ大åĮĸ
    0.07
    严å®Ī
    0.06
    ÑĩаÑĤ
    0.06
    Activations Density 0.007%

    No Known Activations