© 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. 21703
    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
    assa
    -0.08
    /stretch
    -0.07
     jeweilige
    -0.07
    éĿ¡
    -0.07
     Heidel
    -0.07
    onga
    -0.07
    antha
    -0.07
     hò
    -0.07
    endas
    -0.07
    adop
    -0.07
    POSITIVE LOGITS
     -
    0.06
    æľ¬ä¼ģä¸ļ
    0.05
    -t
    0.05
    aut
    0.05
     (
    0.05
    ley
    0.04
     self
    0.04
    念
    0.04
    ئ
    0.04
     separate
    0.04
    Activations Density 0.000%

    No Known Activations