© 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. 18865
    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
    odge
    -0.06
    ksam
    -0.06
    wayne
    -0.05
    åħĭ
    -0.05
     zab
    -0.05
    ócr
    -0.05
    ingers
    -0.05
    æŃ¥
    -0.05
    inger
    -0.05
    Pooling
    -0.05
    POSITIVE LOGITS
     visibilité
    0.06
    ersch
    0.06
    que
    0.05
    ãģ¨ãģĵãĤįãģ§ãģĻ
    0.05
    ÑİÑĤ
    0.05
    æĿ¥ãģ®
    0.05
    ÅĤoÅĽ
    0.05
     каб
    0.05
    åIJİå°Ĩ
    0.05
    _finish
    0.05
    Activations Density 0.000%

    No Known Activations