© 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. 17160
    Prev
    Next
    INDEX
    Explanations

    csv writer or reader

    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
    ؤÙĦاء
    -0.06
    ÙĬ
    -0.06
    i
    -0.05
    aph
    -0.05
    .
    -0.05
    ä¹ĺ
    -0.05
    cura
    -0.05
    inal
    -0.04
     M
    -0.04
     "
    -0.04
    POSITIVE LOGITS
    lau
    0.07
    tecnolog
    0.07
    ighed
    0.07
    maal
    0.07
    她表示
    0.07
    /AFP
    0.07
    عÙģ
    0.07
    .Escape
    0.07
    ãĤĵ
    0.07
    бив
    0.07
    Activations Density 0.008%

    No Known Activations