© 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. 20478
    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
    æĢ
    -0.06
    yk
    -0.05
    ometer
    -0.05
    æľĹ
    -0.05
    缩
    -0.05
    ometers
    -0.05
    deal
    -0.05
    ç¿ģ
    -0.05
     rel
    -0.05
    é²
    -0.05
    POSITIVE LOGITS
    белÑĮ
    0.07
    åħ¨ä¹¦
    0.06
    ä¸į解
    0.06
    ingroup
    0.06
    YP
    0.06
    uevo
    0.06
    (inner
    0.06
    à¯įப
    0.06
    æĢİä¹Īåı¯èĥ½
    0.06
    Èĺ
    0.06
    Activations Density 0.000%

    No Known Activations