© 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. 20090
    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
     tang
    -0.06
    ETS
    -0.05
    å¼ĢæĶ¾çļĦ
    -0.05
    ug
    -0.05
    ollah
    -0.05
     slugg
    -0.05
     Jug
    -0.05
    hein
    -0.05
     varchar
    -0.05
    æŀģåĵģ
    -0.05
    POSITIVE LOGITS
    inker
    0.06
    åIJĮä¸Ģ
    0.06
    asper
    0.05
     îns
    0.05
    æĬķèµĦé£İéĻ©
    0.05
    agger
    0.05
    лÑĮÑĦа
    0.05
     calculation
    0.05
    åĪĽæĸ°
    0.05
     Calculation
    0.05
    Activations Density 0.000%

    No Known Activations