© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18413
    Prev
    Next
    INDEX
    Explanations

    interpretations and imagination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chimp
    -0.07
     ÙħدÙģ
    -0.06
    atto
    -0.06
    ÏĪη
    -0.06
     orgullos
    -0.06
    etine
    -0.06
    æĢ»éĩı
    -0.06
    ç´Ĭä¹±
    -0.06
    æİĴè¡Į
    -0.06
    Listing
    -0.06
    POSITIVE LOGITS
     interpret
    0.09
    解读
    0.09
     interpretation
    0.08
     interpretations
    0.08
    interpret
    0.07
     Interpret
    0.07
     interpreting
    0.07
    解éĩĪ
    0.07
     íķ´ìĦĿ
    0.07
     interpretação
    0.06
    Activations Density 0.012%

    No Known Activations