© 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. 20134
    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
     spr
    -0.06
    åıĤçħ§
    -0.05
    asper
    -0.05
    ç²¾ç¥ŀåĴĮ
    -0.05
    acco
    -0.05
    pler
    -0.05
    /left
    -0.05
    otka
    -0.05
     Either
    -0.05
    éķIJ
    -0.05
    POSITIVE LOGITS
    ifo
    0.06
    abar
    0.06
     kolej
    0.06
    trx
    0.06
    agno
    0.06
     пеÑĢÑģонал
    0.06
    vus
    0.06
    roy
    0.06
    лон
    0.06
    -remove
    0.06
    Activations Density 0.000%

    No Known Activations