© 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. 18980
    Prev
    Next
    INDEX
    Explanations

    digits in number sequences

    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
    HAD
    -0.06
    reff
    -0.06
    åıĭæĥħéĵ¾æİ¥
    -0.06
    à¸Ĺัà¸Ķ
    -0.06
    á»
    -0.06
    è¦ı
    -0.06
     INTERRUPTION
    -0.06
     \"
    -0.05
    ÙħÙĨØ©
    -0.05
    olini
    -0.05
    POSITIVE LOGITS
    мееÑĤÑģÑı
    0.05
    дж
    0.05
    Automatic
    0.05
    asy
    0.05
    eding
    0.05
    ovar
    0.05
    al
    0.05
    ium
    0.05
    CE
    0.05
    èĩªåĬ¨
    0.05
    Activations Density 0.004%

    No Known Activations