© 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. 21174
    Prev
    Next
    INDEX
    Explanations

    off by a day, one behind

    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
    impa
    -0.08
    olica
    -0.08
    à¬Ľ
    -0.08
    éŨåħ³
    -0.08
    áticas
    -0.08
    ATO
    -0.08
    пеÑĢа
    -0.08
    _ASCII
    -0.08
    è¿ľè¿ľçļĦ
    -0.08
    _human
    -0.07
    POSITIVE LOGITS
     depending
    0.09
    ç»ĨèĬĤ
    0.08
    æ¯ķ
    0.07
    æ¼ı
    0.07
     due
    0.07
     discrepancy
    0.07
     details
    0.07
     detail
    0.07
     missed
    0.07
    æŃ£ç¡®çļĦæĺ¯
    0.07
    Activations Density 0.004%

    No Known Activations