© 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. 43926
    Prev
    Next
    INDEX
    Explanations

    assurance and confidence

    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
     etiquette
    -0.07
    çīŁ
    -0.07
    rizione
    -0.07
    ellan
    -0.07
    à¹ĥหà¹īà¸Ħวามสà¸Ļà¹ĥà¸Ī
    -0.07
    请èģĶç³»æĪij们
    -0.07
    йÑģ
    -0.07
    è¦ģéĹ»
    -0.06
    egin
    -0.06
    æķıæĦŁæĢ§
    -0.06
    POSITIVE LOGITS
     confidence
    0.20
    confidence
    0.19
    ä¿¡å¿ĥ
    0.18
     Confidence
    0.18
     ÑĥвеÑĢен
    0.16
     ÑĥвеÑĢенноÑģÑĤÑĮ
    0.16
    èĩªä¿¡
    0.16
     confidently
    0.16
     assurance
    0.16
    ä¿¡å¿ĥçļĦ
    0.16
    Activations Density 0.100%

    No Known Activations