© 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. 17329
    Prev
    Next
    INDEX
    Explanations

    division and calculation of numbers

    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
    软
    -0.06
    èIJ¥
    -0.06
    ç«ĭãģ¦
    -0.06
    abas
    -0.05
    chet
    -0.05
    ATUS
    -0.05
    åľ¨èº«
    -0.05
    软çļĦ
    -0.05
     Yours
    -0.05
    تر
    -0.05
    POSITIVE LOGITS
     ÑĤеÑħно
    0.06
    sky
    0.06
    ixel
    0.05
     remit
    0.05
    enti
    0.05
     remun
    0.05
    å®īå¸Ĥ
    0.05
     hinted
    0.05
    ece
    0.05
    remo
    0.05
    Activations Density 0.057%

    No Known Activations