© 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. 19681
    Prev
    Next
    INDEX
    Explanations

    programming code statements

    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
     khâu
    -0.07
    vers
    -0.06
    cium
    -0.06
    encontre
    -0.06
    亦æĪĸæĺ¯
    -0.06
     suscep
    -0.06
     grop
    -0.06
    åıĪå¤ļ
    -0.06
     Ubicación
    -0.06
    à¹ģà¸ģà¹Ī
    -0.06
    POSITIVE LOGITS
    ulin
    0.05
    {
    0.05
    all
    0.05
     divis
    0.05
    unte
    0.05
    utter
    0.05
    örd
    0.04
    aisse
    0.04
    åĴĮçī¹çĤ¹
    0.04
    im
    0.04
    Activations Density 0.012%

    No Known Activations