© 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. 26694
    Prev
    Next
    INDEX
    Explanations

    probability of picking

    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
    aufnahme
    -0.07
    -parse
    -0.07
    æľªå®Į
    -0.07
    å©Ĩå©Ĩ
    -0.07
    çªģé£ŀ
    -0.07
    åĢºåĬ¡åĪ©æģ¯
    -0.07
    åĩ¡äºº
    -0.07
    ommer
    -0.07
    家äºĭ
    -0.07
    追çĿĢ
    -0.07
    POSITIVE LOGITS
    æ··åIJĪ
    0.11
    æ¦Ĥçİĩ
    0.11
    éļıæľº
    0.11
    çļĦæ¦Ĥçİĩ
    0.11
     Probability
    0.10
    Probability
    0.10
     mixture
    0.10
     probability
    0.09
    æĶ¾åĽŀ
    0.09
    æ··åIJĪçī©
    0.09
    Activations Density 0.043%

    No Known Activations