© 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. 19158
    Prev
    Next
    INDEX
    Explanations

    future events and announcements

    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
    ä¸ĵçĶ¨åıij票
    -0.06
    çķĮ
    -0.06
     belirt
    -0.06
    æĦı
    -0.06
    æĮģä¹ĭ以
    -0.06
    æĬĺä¸įæī£
    -0.06
    è¶ħé¢Ŀ
    -0.06
    æĨ¾
    -0.06
     Telkom
    -0.06
     flexib
    -0.06
    POSITIVE LOGITS
    åĨ³å®ļæĺ¯åIJ¦
    0.06
     in
    0.05
     test
    0.05
    æķıæĦŁçļĦ
    0.05
    æį®è¯´
    0.05
     Test
    0.05
     testing
    0.05
    å·®ä¸įå¤ļäºĨ
    0.05
    olt
    0.05
     Pres
    0.05
    Activations Density 0.165%

    No Known Activations