© 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. 50541
    Prev
    Next
    INDEX
    Explanations

    volatility, variance, standard deviation, variability

    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
    ummer
    -0.07
    年满
    -0.07
    ozo
    -0.07
     hụt
    -0.06
    verts
    -0.06
    δί
    -0.06
    zal
    -0.06
    andat
    -0.06
     Eing
    -0.06
    ç»ijå®ļ
    -0.06
    POSITIVE LOGITS
    Squared
    0.09
    åĿĩåĢ¼
    0.08
    å¹³åĿĩåĢ¼
    0.08
     variance
    0.07
     hired
    0.07
    .mean
    0.07
     measure
    0.07
    åľºåĿĩ
    0.07
    olio
    0.07
     cale
    0.07
    Activations Density 0.006%

    No Known Activations