© 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. 17875
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving `q`

    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
    èĢĢ
    -0.05
    agli
    -0.05
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.05
    èĹı
    -0.05
    ä¸Ģ座
    -0.05
    è¶Ĭ
    -0.05
    çİĩ
    -0.05
    åĮħ
    -0.05
    èĮ¨
    -0.05
    acket
    -0.05
    POSITIVE LOGITS
     bénéfic
    0.08
     türlü
    0.07
    jera
    0.07
     gier
    0.06
     Designs
    0.06
    人士表示
    0.06
     nahr
    0.06
    å¸ĮæľĽèĥ½å¤Ł
    0.06
     ÑģовмеÑģÑĤи
    0.06
    æĿ¥ãģ®
    0.06
    Activations Density 0.008%

    No Known Activations