© 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. 18606
    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
     sno
    -0.08
    uml
    -0.06
    éĻ·
    -0.06
    èĥĮéĿł
    -0.06
     rum
    -0.06
    ạy
    -0.06
    awai
    -0.06
     renom
    -0.06
    véd
    -0.06
     léo
    -0.06
    POSITIVE LOGITS
    åIJ¦
    0.06
    à¸ģว
    0.05
    è¦ģç´§
    0.05
    彩
    0.05
    sau
    0.05
    --
    0.05
    CAPE
    0.05
    äºİä¸Ģ
    0.05
     guaranteed
    0.05
     воп
    0.05
    Activations Density 0.000%

    No Known Activations