© 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. 19043
    Prev
    Next
    INDEX
    Explanations

    founded on principles

    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
     atrap
    -0.09
    è¢ħ
    -0.08
    jenigen
    -0.08
    åIJįåī¯
    -0.08
     ÑĥÑĩаÑģÑĤи
    -0.08
    rolet
    -0.08
    தி
    -0.08
    çľ¼ä¸ŃçļĦ
    -0.08
    omitempty
    -0.08
    clearfix
    -0.07
    POSITIVE LOGITS
     principles
    0.14
     assumptions
    0.12
     foundation
    0.11
     premise
    0.11
     principle
    0.10
     assumption
    0.10
     premises
    0.10
     Principles
    0.10
    çļĦåŁºç¡Ģ
    0.10
    çļĦåİŁåĪĻ
    0.09
    Activations Density 0.263%

    No Known Activations