© 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. 17078
    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
    èĢĥ究
    -0.06
     rem
    -0.05
    çIJĨ论ä¸Ĭ
    -0.05
     up
    -0.05
    lå
    -0.05
    zien
    -0.05
     t
    -0.05
     Rem
    -0.05
    fert
    -0.05
    tot
    -0.05
    POSITIVE LOGITS
    inic
    0.07
    åįļä¸ĸ
    0.07
    æĢ§å¼º
    0.06
    ngh
    0.06
    igente
    0.06
    itim
    0.06
     trúng
    0.06
     Baghd
    0.06
    RESULT
    0.06
     misd
    0.06
    Activations Density 0.000%

    No Known Activations