© 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. 18796
    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
    .beh
    -0.06
    indet
    -0.06
     عج
    -0.06
    åįģ足
    -0.06
     superf
    -0.06
    _basename
    -0.06
     deser
    -0.06
    rac
    -0.06
    IND
    -0.06
    ogan
    -0.06
    POSITIVE LOGITS
     volume
    0.06
    nable
    0.06
     amplify
    0.05
    ам
    0.05
    پرداز
    0.05
    unar
    0.05
     lance
    0.05
    Ļ
    0.05
    oare
    0.05
    Ñĩении
    0.05
    Activations Density 0.000%

    No Known Activations