© 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. 15210
    Prev
    Next
    INDEX
    Explanations

    conjunctions and verbs

    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
     abre
    -0.08
    hati
    -0.08
    顾åIJįæĢĿ
    -0.08
    меÑģÑĤи
    -0.08
     ensued
    -0.08
     appunto
    -0.08
    xCE
    -0.08
     weren
    -0.08
    however
    -0.07
    ibbon
    -0.07
    POSITIVE LOGITS
     undergo
    0.09
    被认为æĺ¯
    0.08
     may
    0.08
     cannot
    0.08
     can
    0.07
     has
    0.07
    æľīä¸Ģå¥Ĺ
    0.07
    èĢħä¹Ł
    0.07
    被认为
    0.07
     should
    0.07
    Activations Density 0.332%

    No Known Activations