© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9168
    Prev
    Next
    INDEX
    Explanations

    currency crisis or war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ðŁı»
    -0.13
    olia
    -0.10
    ¥
    -0.10
    mys
    -0.10
    ï¸
    -0.09
    ends
    -0.09
    éľĵ
    -0.09
    é¹ij
    -0.09
    itty
    -0.09
    tür
    -0.09
    POSITIVE LOGITS
    edImage
    0.09
    eer
    0.09
    zelf
    0.09
    iah
    0.09
     Heb
    0.08
    CTIONS
    0.08
    ouston
    0.08
     Ãĸz
    0.08
    edReader
    0.08
    abinet
    0.08
    Activations Density 0.014%

    No Known Activations