© 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. 18250
    Prev
    Next
    INDEX
    Explanations

    numbers with percent signs

    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
    ally
    -0.06
    ä¼į
    -0.06
    zyw
    -0.06
    irem
    -0.06
    æĽ´å¤ļåħ³äºİ
    -0.05
    ulum
    -0.05
    Sosial
    -0.05
    دÙĬر
    -0.05
    ciuti
    -0.05
    ringen
    -0.05
    POSITIVE LOGITS
    Ø©
    0.08
    rente
    0.07
    zah
    0.07
    го
    0.07
    ness
    0.06
    ison
    0.06
    tä
    0.06
    zz
    0.06
    à¹Į
    0.06
    äch
    0.06
    Activations Density 0.005%

    No Known Activations