© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20496
    Prev
    Next
    INDEX
    Explanations

    encompasses, includes, comprises

    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
    achs
    -0.06
    ript
    -0.05
    ä¹ĭ主
    -0.05
    erville
    -0.05
     Pelo
    -0.05
    pared
    -0.05
    ise
    -0.05
    agama
    -0.05
    ious
    -0.05
    ains
    -0.05
    POSITIVE LOGITS
    ä¸įåĮħæĭ¬
    0.08
    ä¹ŁåĮħæĭ¬
    0.07
    includes
    0.07
     encompasses
    0.07
    included
    0.07
     comprises
    0.07
    è¿ĺåĮħæĭ¬
    0.07
     increÃŃ
    0.06
     comprising
    0.06
    åĮħæĭ¬
    0.06
    Activations Density 0.028%

    No Known Activations