© 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. 24741
    Prev
    Next
    INDEX
    Explanations

    rather than, instead of

    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
    æijĨ
    -0.08
    ess
    -0.08
    ä¹ĭä¸į
    -0.07
    åı¯ä¸į
    -0.07
     indiv
    -0.07
    azos
    -0.07
    åı¯ä½ľä¸º
    -0.07
    uzzi
    -0.06
    åľ¨ä¸»
    -0.06
    åľ¨æľª
    -0.06
    POSITIVE LOGITS
     instead
    0.17
    instead
    0.17
    Instead
    0.15
     Instead
    0.15
     invece
    0.13
    èĢĮéĿŀ
    0.13
     вмеÑģÑĤо
    0.13
     statt
    0.12
    rather
    0.12
     بدÙĦاÙĭ
    0.12
    Activations Density 0.241%

    No Known Activations