© 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. 7719
    Prev
    Next
    INDEX
    Explanations

    FEMA NOAA emergency management

    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
    è¯Ħè®®
    -0.09
    éķľ
    -0.09
    å±ij
    -0.08
    以èī²
    -0.08
    enheim
    -0.08
    ÑıÑī
    -0.08
    ouns
    -0.08
    ometer
    -0.08
    çĽijäºĭ
    -0.08
    驾
    -0.08
    POSITIVE LOGITS
    ä¹°çļĦ
    0.09
    Desk
    0.09
    asil
    0.09
    éķ¿åŁİ
    0.08
    earth
    0.08
    hell
    0.08
    çĶ¨åĵģ
    0.08
    汶å·Ŀ
    0.08
    æĶ¶è´Ń
    0.08
    asel
    0.08
    Activations Density 0.001%

    No Known Activations