© 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. 17761
    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
    wich
    -0.05
    åı£
    -0.05
    æŶéĴĪ
    -0.05
    Âł
    -0.05
    k
    -0.05
    och
    -0.05
    yk
    -0.05
     framing
    -0.05
    ÙĪر
    -0.05
    欢è¿İæĿ¥åĪ°
    -0.05
    POSITIVE LOGITS
    ãĢħ
    0.07
    iable
    0.07
    estina
    0.07
    idia
    0.06
    alow
    0.06
    lables
    0.06
    illot
    0.06
    illion
    0.06
    æ°Ķ象å±Ģ
    0.06
    æĴ¥
    0.06
    Activations Density 0.000%

    No Known Activations