© 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. 20354
    Prev
    Next
    INDEX
    Explanations

    numbers and expressions

    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
    apo
    -0.06
    ÑİÑĢ
    -0.05
    ÑĥÑĩ
    -0.05
    iki
    -0.05
    é«ĺå³°
    -0.05
    åĬłéĢŁ
    -0.05
     mad
    -0.05
    æĺĬ
    -0.05
    ORY
    -0.05
    ies
    -0.05
    POSITIVE LOGITS
    astian
    0.07
    çľģä¼ļ
    0.06
    ewel
    0.06
     perspectiv
    0.06
    çļĦä»»ä½ķ
    0.06
    æĹłè®º
    0.06
    æĹłè®ºå¦Ĥä½ķ
    0.06
    ä»»ä½ķ
    0.06
    ä»»ä½ķä¸Ģæĸ¹
    0.06
    heen
    0.06
    Activations Density 0.031%

    No Known Activations