© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21968
    Prev
    Next
    INDEX
    Explanations

    earthquake followed by tsunami

    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
    .annot
    -0.09
    lectron
    -0.09
    aland
    -0.09
    åŁİ管
    -0.09
    åŁİå¸Ĥ管çIJĨ
    -0.09
    å±Ĥåĩºä¸įç©·
    -0.09
    .mozilla
    -0.09
    ç»ıåİĨ
    -0.09
    æ§į
    -0.08
    å¯Ĩ
    -0.08
    POSITIVE LOGITS
     tsunami
    0.10
    浪
    0.10
    å¨ģåĬĽ
    0.09
    å°ģ
    0.09
    ä¸Ģé¦ĸ
    0.09
     Nap
    0.08
    éĻ¢éĻ¢éķ¿
    0.08
    æ´±
    0.08
    ä¿¡å¿ĥ
    0.08
     Lah
    0.08
    Activations Density 0.040%

    No Known Activations