© 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. 18592
    Prev
    Next
    INDEX
    Explanations

    database management systems

    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
     graft
    -0.06
     cross
    -0.05
    足迹
    -0.05
    æIJŃ
    -0.05
     investig
    -0.05
     started
    -0.05
     tracking
    -0.05
    æĹłç½ª
    -0.05
    èĤ²
    -0.05
    twig
    -0.05
    POSITIVE LOGITS
    大亨
    0.06
     protestors
    0.06
    +":
    0.06
    æķ´ä¸ªéĹ®é¢ĺ
    0.06
    æī¿åİĭ
    0.06
     ìŀħìŀ¥ìĿĦ
    0.06
    å¹½
    0.06
    åİŁåľ°
    0.06
     boyc
    0.06
    ç²¹
    0.06
    Activations Density 0.010%

    No Known Activations