© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19953
    Prev
    Next
    INDEX
    Explanations

    he or she

    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
    /raw
    -0.06
    èµ·äºĨ
    -0.06
    ÙĥØ©
    -0.06
    icale
    -0.05
    ждÑĥÑİ
    -0.05
    ons
    -0.05
    icules
    -0.05
     voulais
    -0.05
    osto
    -0.05
    Virgin
    -0.05
    POSITIVE LOGITS
    enta
    0.06
    io
    0.06
    JAKARTA
    0.06
    ÙĪØ¡
    0.05
     outing
    0.05
    <num
    0.05
    elh
    0.05
     Erdogan
    0.05
    entes
    0.05
    .quit
    0.05
    Activations Density 0.003%

    No Known Activations