© 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. 20007
    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
    اء
    -0.07
    atk
    -0.06
    zÅijd
    -0.06
    pci
    -0.06
     JU
    -0.06
    件
    -0.06
    ebr
    -0.06
    itz
    -0.06
    elib
    -0.06
    ')."
    -0.06
    POSITIVE LOGITS
    agger
    0.06
     strÄĥ
    0.05
    å°ıå§IJ
    0.05
     specific
    0.05
    ione
    0.05
    为äºĨä¿Ŀè¯ģ
    0.05
    ç§ijåѦéĻ¢
    0.05
    .readyState
    0.05
    IBE
    0.05
    ÙĩÙIJ
    0.05
    Activations Density 0.000%

    No Known Activations