© 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. 17390
    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
    ental
    -0.05
    ëĵł
    -0.05
    çĶ±åħ¬åı¸
    -0.05
    ä¸ŃåĽ½å®¶
    -0.05
    vida
    -0.05
     risk
    -0.05
    aign
    -0.05
     Raya
    -0.05
     ray
    -0.05
    enhagen
    -0.05
    POSITIVE LOGITS
     hÃŃbr
    0.06
    ombo
    0.06
    à¹īà¸Ńย
    0.06
    ocere
    0.06
    ä¸ĸ
    0.06
    rob
    0.05
     lĩnh
    0.05
    åĴĮå½±åĵį
    0.05
    ико
    0.05
    focused
    0.05
    Activations Density 0.000%

    No Known Activations