© 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. 17328
    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
    -0.06
     i
    -0.06
    !
    -0.06
    reat
    -0.06
     Deep
    -0.05
     deep
    -0.05
    oj
    -0.05
    èīº
    -0.05
     b
    -0.05
     L
    -0.05
    POSITIVE LOGITS
    ç¾ļç¾Ĭ
    0.07
    clist
    0.07
    cko
    0.07
     manh
    0.07
     contactez
    0.07
     mancan
    0.06
    å¤įåİŁ
    0.06
    ucie
    0.06
    loses
    0.06
    æķĻèĤ²åѦçĶŁ
    0.06
    Activations Density 0.000%

    No Known Activations