© 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. 20654
    Prev
    Next
    INDEX
    Explanations

    provider of

    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
    çļĦåIJ§
    -0.07
    ächt
    -0.07
    urat
    -0.07
    erima
    -0.07
    atkan
    -0.07
    æĹłå¾®ä¸įèĩ³
    -0.07
    ä»ĸãģ«ãĤĤ
    -0.06
     تÙĤد
    -0.06
    zuh
    -0.06
    åĸ°
    -0.06
    POSITIVE LOGITS
    0.04
    èĩª
    0.04
    Ø°
    0.04
    дел
    0.04
     bloody
    0.04
    ied
    0.04
    irected
    0.04
    äºĨ
    0.04
    anded
    0.04
     environs
    0.04
    Activations Density 0.011%

    No Known Activations