© 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. 29947
    Prev
    Next
    INDEX
    Explanations

    tau, or tau-related biological/physical 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
    ividual
    -0.10
    ustry
    -0.08
    en
    -0.08
    serter
    -0.08
    ek
    -0.08
     raya
    -0.07
    áĥ£áĥłáĥĺ
    -0.07
    ydd
    -0.07
    ëį°
    -0.06
    stry
    -0.06
    POSITIVE LOGITS
    ÏģαÏĢε
    0.09
    celli
    0.09
    алÑĮÑı
    0.09
    allis
    0.09
    abbit
    0.08
    ìį¨
    0.08
    unami
    0.08
     './../
    0.08
    à¹Īวัà¸Ļ
    0.08
    esseract
    0.08
    Activations Density 0.004%

    No Known Activations