© 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. 57691
    Prev
    Next
    INDEX
    Explanations

    expected value, probability

    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
     stuck
    -0.08
    ¢
    -0.07
    æĥ°
    -0.07
    stub
    -0.07
    bund
    -0.06
    klink
    -0.06
    bands
    -0.06
     sticks
    -0.06
    pest
    -0.06
    LOPT
    -0.06
    POSITIVE LOGITS
     expectation
    0.09
    æ¦Ĥçİĩ
    0.08
     expectations
    0.08
    æīĶåĪ°
    0.08
     randomness
    0.07
    æ»Ķ
    0.07
     probabil
    0.07
     Probability
    0.07
    expect
    0.07
     probability
    0.07
    Activations Density 0.009%

    No Known Activations