© 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. 21815
    Prev
    Next
    INDEX
    Explanations

    equivalent, SUB, join, product rule, paste, composition

    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
    elang
    -0.07
    ERIC
    -0.06
     precinct
    -0.06
     Waterloo
    -0.06
    store
    -0.06
    æĹłæļĩ
    -0.06
    æĹłçĹĽ
    -0.06
    mond
    -0.06
     ??
    -0.06
     Pri
    -0.06
    POSITIVE LOGITS
    quita
    0.08
     Espe
    0.08
     ÑįкÑģп
    0.08
    ismet
    0.08
    缸å½ĵäºİ
    0.08
    æĶĺ
    0.08
     equivalent
    0.08
    ajem
    0.07
    çŃīæķĪ
    0.07
     Equivalent
    0.07
    Activations Density 0.005%

    No Known Activations