© 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. 17992
    Prev
    Next
    INDEX
    Explanations

    boolean enable/mode

    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¸Ģç«Ļ
    -0.07
     switching
    -0.06
    нагÑĢа
    -0.06
    éĤ£åº§
    -0.06
    幸
    -0.06
    ingle
    -0.06
    itters
    -0.06
    -switch
    -0.06
    å·¦åı³
    -0.06
    ÑĢÑĥг
    -0.06
    POSITIVE LOGITS
    ogl
    0.06
    æİĴæ°´
    0.06
    ذة
    0.05
     hooked
    0.05
    满èħĶ
    0.05
    å¿ĥæĥ³
    0.05
    czyk
    0.05
    IAL
    0.05
     اÙĦÙĪ
    0.05
    失åİ»
    0.05
    Activations Density 0.003%

    No Known Activations