© 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. 21863
    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
    usch
    -0.06
    uden
    -0.06
    ç½®
    -0.06
    ç»ıçIJĨ
    -0.06
    impat
    -0.06
    leg
    -0.05
    èĩĤ
    -0.05
    umo
    -0.05
    hdl
    -0.05
    oom
    -0.05
    POSITIVE LOGITS
    大éĩıçļĦ
    0.07
    lear
    0.06
    æµ·éĩıçļĦ
    0.06
    çļĦ大éĩı
    0.06
    gist
    0.06
    rase
    0.06
    大éĩı
    0.05
    yiz
    0.05
     limits
    0.05
    缸çĶŁ
    0.05
    Activations Density 0.000%

    No Known Activations