© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55167
    Prev
    Next
    INDEX
    Explanations

    determine evidence of efficacy

    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
    Negative Logits
    æĸ¯çī¹
    -0.07
    æĭ¾
    -0.07
    Õ¸ÖĢ
    -0.07
    ếch
    -0.07
    ëŀ©
    -0.06
    à¸ķิà¸ģ
    -0.06
     ÅĻe
    -0.06
    æĹ©å·²
    -0.06
     Doma
    -0.06
    ela
    -0.06
    POSITIVE LOGITS
     statistically
    0.10
     randomness
    0.08
    åľ¨åħ¨çľģ
    0.08
     evidence
    0.08
    ixo
    0.07
    æĢĢçĸij
    0.07
    端æŃ£
    0.07
    è¯ģæį®
    0.07
    ÑĢоли
    0.07
    èĩ³å°ijåľ¨
    0.07
    Activations Density 0.028%

    No Known Activations