© 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. 22127
    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
     abstract
    -0.06
     ÑģебÑı
    -0.06
    ä¿¡å°ģ
    -0.06
    壤
    -0.05
    artig
    -0.05
    sti
    -0.05
     correlated
    -0.05
    ãģªãģįãĤĥ
    -0.05
    è´¨çļĦ
    -0.05
     envelop
    -0.05
    POSITIVE LOGITS
    ade
    0.08
    evÅ¡ÃŃm
    0.07
    inga
    0.06
     )*
    0.06
    ure
    0.06
    ']))
    0.06
    odate
    0.06
    atcher
    0.06
    )))),
    0.06
    odge
    0.06
    Activations Density 0.000%

    No Known Activations