© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19721
    Prev
    Next
    INDEX
    Explanations

    roman numerals and numbers

    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
     su
    -0.06
    åİ»è´Ńä¹°
    -0.06
    afir
    -0.06
    æĪijåij¢
    -0.05
    empel
    -0.05
    åħľ
    -0.05
    gress
    -0.05
    -src
    -0.05
     inst
    -0.05
    nev
    -0.05
    POSITIVE LOGITS
    ä»ķ
    0.06
    ÑĩиÑģ
    0.05
    åĶ
    0.05
    ÑĪке
    0.05
    avimo
    0.05
    estone
    0.05
    à¹ĥà¸ģลà¹ī
    0.05
     dominated
    0.05
    inari
    0.05
     orth
    0.05
    Activations Density 0.002%

    No Known Activations