© 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. 20239
    Prev
    Next
    INDEX
    Explanations

    latitude, longitude, message

    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
    Proto
    -0.06
     Merk
    -0.06
    åıĬåħ¶èĩªåĬ¨åĮĸ
    -0.05
    æĽ¸è¨ĺ
    -0.05
    éĤ£åı¥è¯Ŀ
    -0.05
    å½¢å¼ı
    -0.05
     fascinated
    -0.05
    è¿ĩæŶ
    -0.05
    该æĸ¹æ³ķ
    -0.05
     mine
    -0.05
    POSITIVE LOGITS
    å·¨
    0.06
    EMPL
    0.05
    oster
    0.05
    ä¸įä»ħæĺ¯
    0.05
    山峰
    0.05
    trag
    0.05
    夫
    0.05
     ung
    0.05
    оÑģÑĤÑĮ
    0.05
     Estad
    0.05
    Activations Density 0.006%

    No Known Activations