© 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. 18864
    Prev
    Next
    INDEX
    Explanations

    init, references, calculations, ;amp, pregunta, ear, DC, .Field

    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
    بÙĦ
    -0.05
    ret
    -0.05
    av
    -0.05
    ä¸įæĪIJ
    -0.05
    æĪĺçķ¥æĢ§
    -0.05
    iqu
    -0.05
    ä¸İåħ±
    -0.05
    åıĸåĨ³äºİ
    -0.05
    çļĦæĥħ
    -0.05
    lex
    -0.05
    POSITIVE LOGITS
    รัมยà¹Į
    0.06
    åħĮ
    0.06
    鸯
    0.06
    anggap
    0.06
    æĸĩæķĻ
    0.06
    beth
    0.06
    à¸Ľà¸±à¸ĩ
    0.06
    ÃīN
    0.06
    ä¼łç»ŁæĸĩåĮĸçļĦ
    0.06
     plung
    0.06
    Activations Density 0.025%

    No Known Activations