© 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. 18810
    Prev
    Next
    INDEX
    Explanations

    part of a phrase or sentence

    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
    绣
    -0.06
    us
    -0.05
     ust
    -0.05
    коÑģÑĤÑĮÑİ
    -0.05
    æĽ
    -0.05
    kan
    -0.05
    è¿ĻäºĽæķ°æį®
    -0.05
    åīįæıIJä¸ĭ
    -0.05
    mente
    -0.05
     ÑģодеÑĢж
    -0.05
    POSITIVE LOGITS
    andin
    0.06
    yku
    0.06
    urun
    0.06
    AGED
    0.06
    ائÙħ
    0.06
    attern
    0.06
    воÑĢ
    0.06
     заби
    0.06
    AGEM
    0.05
    伤害
    0.05
    Activations Density 0.019%

    No Known Activations