© 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. 22173
    Prev
    Next
    INDEX
    Explanations

    make use or either

    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
    rawd
    -0.08
    _every
    -0.07
     اØŃتÙħ
    -0.06
     khe
    -0.06
    impin
    -0.06
     tất
    -0.06
    笳
    -0.06
    عÙĦÙĨت
    -0.06
    åı¯èĥ½è¢«
    -0.06
    æŃ¹
    -0.06
    POSITIVE LOGITS
     either
    0.08
    or
    0.07
    æĪĸåħ¶
    0.07
    æĪĸèĢħ
    0.07
     or
    0.06
    æĪĸä¸į
    0.06
    either
    0.06
     entweder
    0.06
    è¿Ļç§įåģļæ³ķ
    0.06
    Either
    0.06
    Activations Density 0.159%

    No Known Activations