© 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. 17457
    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
    owski
    -0.06
    WISE
    -0.06
     suss
    -0.06
     ÙĪÙĩÙħ
    -0.05
    owanie
    -0.05
    finity
    -0.05
    常èŃĺ
    -0.05
    artes
    -0.05
    è·
    -0.05
     kindly
    -0.05
    POSITIVE LOGITS
    oad
    0.06
    éĵ¶æ²³
    0.05
    das
    0.05
    resse
    0.05
     سرا
    0.05
    presso
    0.05
    ä¸Ģä½ĵ
    0.05
    ç»İ
    0.05
    åĥ§
    0.05
    gor
    0.05
    Activations Density 0.000%

    No Known Activations