© 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. 21900
    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
    coa
    -0.05
    unker
    -0.05
    èĢĮå·²
    -0.05
    urn
    -0.05
    ourt
    -0.05
    åĪļä¸Ģ
    -0.05
    å®¡æŁ¥
    -0.05
    ä¸įèĪį
    -0.05
    rt
    -0.05
    å¾ĭ
    -0.05
    POSITIVE LOGITS
    iez
    0.06
    ijat
    0.06
    irá
    0.06
    λλη
    0.06
    æ·¡æ¼ł
    0.06
    åIJij被åijĬ
    0.06
    å¯ĦãģĽ
    0.06
    ลุ
    0.05
    ç±³äºļ
    0.05
    adia
    0.05
    Activations Density 0.000%

    No Known Activations