© 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. 20887
    Prev
    Next
    INDEX
    Explanations

    loose clothing

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    els
    -0.06
    zel
    -0.05
    urs
    -0.05
     int
    -0.05
    uns
    -0.05
    ERT
    -0.05
     adult
    -0.05
    int
    -0.05
    /embed
    -0.05
    tring
    -0.05
    POSITIVE LOGITS
    åĢįå¢ŀ
    0.07
     Sizes
    0.06
    BUF
    0.06
    象山
    0.06
     volumes
    0.06
    volume
    0.06
     volumen
    0.06
     responsiveness
    0.06
    仪å¼ıæĦŁ
    0.06
    spre
    0.06
    Activations Density 0.008%

    No Known Activations