© 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. 27987
    Prev
    Next
    INDEX
    Explanations

    estimation and estimators

    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
    cdb
    -0.07
    enze
    -0.07
    enheim
    -0.07
    _indent
    -0.07
    linked
    -0.07
    -linked
    -0.07
    illar
    -0.07
     conquered
    -0.07
     inhabited
    -0.07
    éĵº
    -0.07
    POSITIVE LOGITS
    估计
    0.09
     estimator
    0.09
    ä¼°
    0.09
    Statistic
    0.08
    estim
    0.08
     estim
    0.08
     estimates
    0.08
     Stat
    0.08
     estimate
    0.07
     unbiased
    0.07
    Activations Density 0.011%

    No Known Activations