© 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. 17116
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    irro
    -0.07
    entar
    -0.06
    åIJ¹åĵį
    -0.06
    haf
    -0.06
     Anten
    -0.06
     Kare
    -0.06
    haust
    -0.06
     mạc
    -0.06
     vall
    -0.06
    ubro
    -0.06
    POSITIVE LOGITS
    $
    0.05
    seg
    0.05
    iance
    0.05
     perpet
    0.05
    "
    0.05
    Y
    0.05
    ÑģледÑĥ
    0.05
    代
    0.05
     nghĩa
    0.05
     rit
    0.05
    Activations Density 0.227%

    No Known Activations