© 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. 20913
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    inata
    -0.06
    éĢĨ天
    -0.06
    æĬĹ
    -0.06
     DÃ¥
    -0.06
     arrog
    -0.06
    à¸Ķย
    -0.06
    heck
    -0.05
     Sax
    -0.05
     menger
    -0.05
    inv
    -0.05
    POSITIVE LOGITS
    ç§
    0.06
    cribing
    0.05
     mak
    0.05
    æ»
    0.05
    bod
    0.05
    ÑĢÑıдÑĥ
    0.05
    çĥŃ
    0.05
     Pec
    0.05
     cou
    0.05
    çľł
    0.05
    Activations Density 0.000%

    No Known Activations