© 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. 19145
    Prev
    Next
    INDEX
    Explanations

    package, readers, temperature, size, medical terms

    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
     commenting
    -0.06
    Ïīμα
    -0.06
    \-
    -0.06
    angsa
    -0.06
    piece
    -0.06
     idé
    -0.06
    èĩªå·±çļĦ
    -0.06
    ÏĥÏĦα
    -0.06
    à¹ģà¸Ķà¸Ļ
    -0.06
    .dst
    -0.06
    POSITIVE LOGITS
    彬
    0.06
     '
    0.05
    Ĵ
    0.05
    amar
    0.05
    rise
    0.05
     sustained
    0.05
    .photos
    0.05
    é¢ľ
    0.05
    æľªå®Įå¾ħç»Ń
    0.05
    auer
    0.05
    Activations Density 0.002%

    No Known Activations