© 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. 18872
    Prev
    Next
    INDEX
    Explanations

    cost amounts and currency

    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
    ouse
    -0.07
    orable
    -0.06
    aho
    -0.06
     insignificant
    -0.06
    cool
    -0.06
    extr
    -0.06
    çŁ³èĨı
    -0.06
    à¸ı
    -0.05
    Ùĩاد
    -0.05
    oarece
    -0.05
    POSITIVE LOGITS
    ÙĨد
    0.07
    shaw
    0.06
    son
    0.06
    richt
    0.06
    Ãłu
    0.06
    cran
    0.06
    ross
    0.05
     изб
    0.05
    wise
    0.05
     Manc
    0.05
    Activations Density 0.009%

    No Known Activations