© 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. 22094
    Prev
    Next
    INDEX
    Explanations

    services

    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
    ä¸Ģ大
    -0.05
    缮æłĩä»»åĬ¡
    -0.05
    cle
    -0.05
     Tum
    -0.05
    åIJĪä½ľé¡¹çĽ®
    -0.05
    æĬķèµĦé£İéĻ©
    -0.05
     acts
    -0.05
    ÄĻ
    -0.05
    ç»ıèIJ¥é¡¹çĽ®
    -0.05
    alem
    -0.04
    POSITIVE LOGITS
    éĿŀçī©è´¨
    0.07
    awat
    0.06
     inscrire
    0.06
    ornado
    0.06
    akon
    0.06
    æĹłä¸Ģ
    0.06
     guna
    0.06
    æ»´æ»´
    0.06
     austerity
    0.06
    aggi
    0.06
    Activations Density 0.005%

    No Known Activations