© 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. 17851
    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
    allis
    -0.07
    asto
    -0.06
    kind
    -0.06
    all
    -0.05
     ì¹ĺ
    -0.05
    structured
    -0.05
     شاÙĨ
    -0.05
    åħįåİ»
    -0.05
    entries
    -0.05
    èĢ½è¯¯
    -0.05
    POSITIVE LOGITS
    peror
    0.05
    inity
    0.05
    æĸ¼
    0.05
    義
    0.05
    æĽ¾è¢«
    0.05
    ết
    0.05
     BÃŃch
    0.05
    haf
    0.05
    écution
    0.05
    ä¸Ńåħ¬
    0.05
    Activations Density 0.000%

    No Known Activations