© 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. 18360
    Prev
    Next
    INDEX
    Explanations

    GTX 560 Ti

    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
     intricate
    -0.06
    asiat
    -0.06
    vang
    -0.06
     wyp
    -0.05
    yip
    -0.05
    æĬľãģį
    -0.05
     arcs
    -0.05
    jours
    -0.05
    kee
    -0.05
    arters
    -0.05
    POSITIVE LOGITS
    åħ¬
    0.05
    ebra
    0.05
    âĸłâĸł
    0.05
     Äijiá»ĥn
    0.05
    gren
    0.05
    à¥Ĥस
    0.05
    æģ
    0.05
    æĻļ
    0.05
    åĽłåħ¬
    0.05
    tecnolog
    0.05
    Activations Density 0.012%

    No Known Activations