© 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. 18087
    Prev
    Next
    INDEX
    Explanations

    firefox appeal

    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
     truc
    -0.05
     influence
    -0.05
    æĬ±è´Ł
    -0.05
    ä¸Ģæīĭ
    -0.05
     success
    -0.05
    å®¶åľ¨
    -0.05
    trat
    -0.05
    ä¼ĺèī¯ä¼łç»Ł
    -0.05
    -making
    -0.05
    rit
    -0.05
    POSITIVE LOGITS
    ware
    0.07
    ourmet
    0.06
    à¹Īาà¸Ļ
    0.06
    versa
    0.06
    çĶŁåij½ä¸ŃçļĦ
    0.06
    ouver
    0.06
    éħįå¤ĩ
    0.06
    ynamic
    0.06
    خر
    0.06
    exit
    0.05
    Activations Density 0.001%

    No Known Activations