© 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. 17014
    Prev
    Next
    INDEX
    Explanations

    .com domain names

    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
    ipple
    -0.06
    æħ·
    -0.06
    ç»ı审çIJĨ
    -0.06
    -upper
    -0.06
    /topic
    -0.06
    貿
    -0.06
     distanci
    -0.06
    HEEL
    -0.06
     zre
    -0.06
    loor
    -0.06
    POSITIVE LOGITS
    bern
    0.05
    azing
    0.05
    ber
    0.05
    éħį
    0.05
    çĹĩçļĦ
    0.05
     mi
    0.05
    etem
    0.05
    etary
    0.05
    åģı
    0.05
     und
    0.04
    Activations Density 0.257%

    No Known Activations