© 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. 20668
    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
    edly
    -0.08
    cim
    -0.07
    é«ĺ度çļĦ
    -0.07
    ças
    -0.07
    công
    -0.06
    APH
    -0.06
    ancement
    -0.06
    çªģåĩºçļĦ
    -0.06
    pter
    -0.06
    åį³æĹ¥èµ·
    -0.06
    POSITIVE LOGITS
    ail
    0.05
    ulling
    0.05
     sembl
    0.05
    æѤ
    0.05
    (
    0.05
    æ±ģ
    0.05
    ernes
    0.05
    'd
    0.04
    caled
    0.04
    延
    0.04
    Activations Density 0.000%

    No Known Activations