© 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. 22185
    Prev
    Next
    INDEX
    Explanations

    without permission

    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
    æĭīåħĭ
    -0.06
    ÃŃmos
    -0.06
    åįĥéĩĮ
    -0.06
     pract
    -0.06
    ä¸Ĭä¸ĢæĿ¡
    -0.06
    åĨĻåĪ°
    -0.06
    жели
    -0.06
     usufruire
    -0.06
    fort
    -0.06
    ض
    -0.05
    POSITIVE LOGITS
    èŃ
    0.06
    arne
    0.05
    ÑĢавни
    0.05
    yen
    0.05
     contempor
    0.05
     rub
    0.05
    모
    0.05
    pany
    0.05
    ANN
    0.05
    èĤ¤
    0.05
    Activations Density 0.011%

    No Known Activations