© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22615
    Prev
    Next
    INDEX
    Explanations

    earthquake and related activity

    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
    罨
    -0.10
    bsite
    -0.09
    èĮ¸
    -0.09
    ajo
    -0.08
    èĮī
    -0.08
    aram
    -0.08
    ãĥĻãĥ³
    -0.08
    bench
    -0.08
    宸
    -0.08
    æķ£
    -0.08
    POSITIVE LOGITS
    åľ°éľĩ
    0.17
     earthquake
    0.12
     earthquakes
    0.12
    éľĩ
    0.11
    quake
    0.11
    itters
    0.10
     quake
    0.09
    å°ıåŀĭ
    0.09
    å¼Ħå¾Ĺ
    0.08
    å¹³éĿĻ
    0.08
    Activations Density 0.054%

    No Known Activations