© 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. 22259
    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
    quen
    -0.07
    åĦ¿çļĦ
    -0.06
    ä¸įè¾¾
    -0.06
    åı£éķĩ
    -0.06
     quir
    -0.06
    ذة
    -0.06
    Einst
    -0.06
    æ¹¾åĮº
    -0.06
    zÄĥ
    -0.06
    adata
    -0.06
    POSITIVE LOGITS
    om
    0.05
    neb
    0.05
     centrale
    0.05
     pet
    0.05
     capit
    0.05
    åĽ¤
    0.05
    å¿Ĩ
    0.04
     presente
    0.04
     sociale
    0.04
    he
    0.04
    Activations Density 0.000%

    No Known Activations