© 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. 19929
    Prev
    Next
    INDEX
    Explanations

    is here to

    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
    arder
    -0.07
    üten
    -0.07
    审å®ļ
    -0.07
    æ¯ıä¸Ģ份
    -0.07
    nez
    -0.07
    ãģĹãģĭãģ£ãģŁãģ§ãģĻ
    -0.07
    веÑĢÑĪенÑģÑĤво
    -0.07
    ¶ļ
    -0.06
    æŶéĹ´æĿ¥
    -0.06
    AVOR
    -0.06
    POSITIVE LOGITS
    åħ¶æŀĹ
    0.06
     according
    0.05
    æį®
    0.05
    å¾Ĺ
    0.05
    积
    0.05
    æ°ı
    0.05
    KE
    0.05
    æ³ķ令
    0.05
    c
    0.05
    ç«ĭ
    0.05
    Activations Density 0.007%

    No Known Activations