© 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. 17862
    Prev
    Next
    INDEX
    Explanations

    "a" followed by specific nouns

    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
     capit
    -0.07
    ä¹ı
    -0.06
    æ®ĸ
    -0.06
     vypl
    -0.06
     outcome
    -0.06
    ặn
    -0.06
    öd
    -0.06
     kap
    -0.06
    _associ
    -0.05
    YP
    -0.05
    POSITIVE LOGITS
    ta
    0.06
    esm
    0.06
    èĮ¬
    0.06
    æķ°æį®æĿ¥æºIJ
    0.05
    пÑĢа
    0.05
    isir
    0.05
    miet
    0.05
    nia
    0.05
    ebra
    0.05
     Ùģارس
    0.05
    Activations Density 0.295%

    No Known Activations