© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18183
    Prev
    Next
    INDEX
    Explanations

    concerts and tours

    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
    è¹
    -0.06
    anguage
    -0.06
    伶ä¿IJ
    -0.06
    alom
    -0.06
    è¿IJçĶ¨åĪ°
    -0.05
    еÑĤÑĢо
    -0.05
    æ³³
    -0.05
    æ±łä¸Ń
    -0.05
    رÙģØ©
    -0.05
     others
    -0.05
    POSITIVE LOGITS
    hosts
    0.06
    iasm
    0.05
    à¸Ħà¸Ńà¸Ļ
    0.05
    STACK
    0.05
    å®īåħ¨æ£ĢæŁ¥
    0.05
    å·¡æ¼Ķ
    0.05
     touring
    0.05
     Biblio
    0.05
    ä¸Ń转
    0.05
     NSA
    0.05
    Activations Density 0.077%

    No Known Activations