© 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. 17150
    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
    太éĥİ
    -0.06
    åħ¸åŀĭçļĦ
    -0.06
    åħĪéĶĭ
    -0.05
    åħ¸åŀĭ
    -0.05
    æŃª
    -0.05
    çľī
    -0.05
    æīĵçļĦ
    -0.05
    æ²īéĩį
    -0.05
     Listing
    -0.05
    éĩijçļĦ
    -0.05
    POSITIVE LOGITS
    èijĨ
    0.07
    èĢĮè¿ĩ
    0.06
     pourrez
    0.06
    Policy
    0.06
    truct
    0.06
    ler
    0.06
    ãĤ«æľĪ
    0.06
     кÑĬде
    0.06
    Epoch
    0.06
    ép
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.