© 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. 19058
    Prev
    Next
    INDEX
    Explanations

    value="

    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
    设å¤ĩè¿Ľè¡Į
    -0.06
    agem
    -0.06
    \\/
    -0.05
    è¿«
    -0.05
    not
    -0.05
    çŁŃçļĦ
    -0.05
    ä»ĸ们认为
    -0.05
    ippi
    -0.05
    æĪĸéĿŀ
    -0.05
    maa
    -0.05
    POSITIVE LOGITS
    éĢĤçĶ¨
    0.06
    гÑĢад
    0.06
     Inns
    0.05
    à¸ģำลัà¸ĩ
    0.05
    éļĶçĿĢ
    0.05
     ero
    0.05
    èµĦ
    0.05
    اÙĦÙĬ
    0.05
    ibraltar
    0.05
    unds
    0.05
    Activations Density 0.001%

    No Known Activations