© 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. 6356
    Prev
    Next
    INDEX
    Explanations

    Fukushima nuclear accident 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
    èĩºåįĹå¸Ĥ
    -0.09
    æľīåĬ©
    -0.09
    çľ¼çľĭ
    -0.09
    .creator
    -0.09
    æį£
    -0.09
    ItemCount
    -0.08
    缴éĢļ车
    -0.08
    æĦ£
    -0.08
    IRS
    -0.08
    ä¸įç»ı
    -0.08
    POSITIVE LOGITS
     tsunami
    0.10
     Uri
    0.10
    å¾ģæ±Ĥ
    0.09
     Fukushima
    0.09
     bail
    0.08
    嵯
    0.08
    (uri
    0.08
    Ts
    0.08
    çģ¾
    0.08
     Ts
    0.08
    Activations Density 0.065%

    No Known Activations