© 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. 19857
    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
    de
    -0.05
    aps
    -0.05
    irteen
    -0.05
     seven
    -0.05
     inaugural
    -0.05
     ab
    -0.05
    è°ģæĿ¥
    -0.04
     оÑģобого
    -0.04
     Ar
    -0.04
     Al
    -0.04
    POSITIVE LOGITS
    Blan
    0.07
    大éĢļ
    0.07
    istante
    0.06
    peat
    0.06
    icano
    0.06
    åĪ°èĢģ
    0.06
    presenta
    0.06
     –**
    0.06
    éľ²
    0.06
    loff
    0.06
    Activations Density 0.000%

    No Known Activations