© 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. 57366
    Prev
    Next
    INDEX
    Explanations

    estimating functions or quantities

    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
    ôn
    -0.07
     thi
    -0.07
    enk
    -0.06
    éº
    -0.06
     Thi
    -0.06
    çľ·
    -0.06
     ken
    -0.06
    çĶ¸
    -0.06
    conte
    -0.06
     Aster
    -0.06
    POSITIVE LOGITS
     estimated
    0.10
    ä¸įåĩĨç¡®
    0.10
     Estimated
    0.10
     estimate
    0.10
    估计
    0.09
    ä»ĸ们认为
    0.09
     estimation
    0.09
    _est
    0.09
     estim
    0.09
     estimator
    0.09
    Activations Density 0.012%

    No Known Activations