© 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. 19967
    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
     sund
    -0.06
    endif
    -0.05
    ç»´æĮģ
    -0.05
     dec
    -0.05
    ertos
    -0.05
    вл
    -0.05
    fre
    -0.05
    kol
    -0.05
    fallen
    -0.05
    f
    -0.05
    POSITIVE LOGITS
    usher
    0.06
    ëį°ìĿ´
    0.05
    -desktop
    0.05
     confron
    0.05
    à¹Ĥà¸Ń
    0.05
    rieg
    0.05
     NotImplemented
    0.05
    æ·±å¤ľ
    0.05
    oft
    0.05
    åĢįå¢ŀ
    0.05
    Activations Density 0.000%

    No Known Activations