© 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. 19162
    Prev
    Next
    INDEX
    Explanations

    expectations and standards

    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
    saf
    -0.07
    çļĦä¼ĺåĬ¿
    -0.07
    LEE
    -0.07
    è¢ħ
    -0.06
    æľīæķĪçļĦ
    -0.06
     gá»įn
    -0.06
    stash
    -0.06
    WISE
    -0.06
     chaude
    -0.06
     \/
    -0.06
    POSITIVE LOGITS
     expectations
    0.19
     expectation
    0.16
     Erwartungen
    0.15
    æłĩåĩĨè¦ģæ±Ĥ
    0.15
     standards
    0.14
     Expect
    0.14
    æľŁæľĽ
    0.14
    expect
    0.14
    Expect
    0.14
     EXPECT
    0.13
    Activations Density 0.121%

    No Known Activations