© 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. 21384
    Prev
    Next
    INDEX
    Explanations

    **forum**

    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
    wie
    -0.05
     timeouts
    -0.05
    teg
    -0.05
    aac
    -0.05
     typeid
    -0.05
    eleg
    -0.05
    Elimina
    -0.05
    ottima
    -0.05
    zione
    -0.05
    åĬłæĭ¿å¤§
    -0.05
    POSITIVE LOGITS
    س
    0.06
    shire
    0.06
    бÑĥдÑĮÑĤе
    0.06
    ÙĬØ©
    0.06
     sức
    0.06
    sis
    0.06
    ãĥĸãĥĥãĤ¯
    0.06
     roulant
    0.05
    éļĻ
    0.05
    oints
    0.05
    Activations Density 0.006%

    No Known Activations