© 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. 18100
    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
    iller
    -0.06
    ç»ĦåĴĮ
    -0.06
    gau
    -0.06
    atot
    -0.06
    DITION
    -0.06
     fundamentally
    -0.06
    thers
    -0.06
    çĢı
    -0.06
    åIJĦç§įéĹ®é¢ĺ
    -0.06
    ãģĺãĤģãģ¦
    -0.06
    POSITIVE LOGITS
    æģIJ
    0.06
    çĦī
    0.05
    åįİ人
    0.05
    ipy
    0.05
    uko
    0.05
    æĸij
    0.05
    ä¸Ń度
    0.05
    ukes
    0.05
    éķ¿èĢģ
    0.05
    erp
    0.05
    Activations Density 0.000%

    No Known Activations