© 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. 20791
    Prev
    Next
    INDEX
    Explanations

    cit or tag

    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
    ³
    -0.07
    å²Ĺ
    -0.07
    çļĩåĨł
    -0.06
    witz
    -0.06
    MG
    -0.06
     incompetence
    -0.06
    oons
    -0.05
    duÄŁ
    -0.05
    à¹Īวà¸ĩ
    -0.05
     ngũ
    -0.05
    POSITIVE LOGITS
    0.07
    {{{
    0.05
    ваемаÑı
    0.05
     gad
    0.05
    åģĩ
    0.05
    adak
    0.05
     ha
    0.05
    iet
    0.05
    è¾ĥ大çļĦ
    0.05
     Union
    0.05
    Activations Density 0.004%

    No Known Activations