© 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. 18371
    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
    æĸ¯
    -0.05
    —
    -0.05
     V
    -0.05
     i
    -0.05
     f
    -0.04
    i
    -0.04
    é«ĺæķĪ
    -0.04
    è¦ģ
    -0.04
    å¡ij
    -0.04
     S
    -0.04
    POSITIVE LOGITS
    atezza
    0.08
    assis
    0.07
    enie
    0.07
     **:**
    0.07
     .**
    0.07
     berat
    0.07
     nutris
    0.07
    ÑĢовиÑĩ
    0.07
     -**
    0.07
    trimmed
    0.07
    Activations Density 0.000%

    No Known Activations