© 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. 19932
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with choices

    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
    å¼ıåĴĮ
    -0.05
    inx
    -0.05
     proper
    -0.05
    åĬ¡
    -0.05
    -board
    -0.05
     سرÙħ
    -0.05
    ä½ĵåĴĮ
    -0.05
    ists
    -0.05
     ges
    -0.05
    ä¸ĭè§Ĵ
    -0.05
    POSITIVE LOGITS
    æĹ©
    0.06
    icano
    0.06
    TEE
    0.06
     estimado
    0.06
    unas
    0.05
    TF
    0.05
    زش
    0.05
    paro
    0.05
    ظاÙĩر
    0.05
    æŀľçľŁ
    0.05
    Activations Density 0.008%

    No Known Activations