© 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. 53482
    Prev
    Next
    INDEX
    Explanations

    earthquakes and disasters

    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
    orns
    -0.10
    ä¸Ģåı£
    -0.09
    ovy
    -0.09
    _PB
    -0.09
    丰满
    -0.09
    å¼ĥ
    -0.09
    sworth
    -0.09
    Ñģен
    -0.09
    èĢĺ
    -0.08
    .sg
    -0.08
    POSITIVE LOGITS
    èĩªçĦ¶çģ¾å®³
    0.13
    åľ°éľĩ
    0.13
     earthquakes
    0.11
    æļ´éĽ¨
    0.11
    çģ¾å®³
    0.10
    åĴĨ
    0.10
    é¢ij
    0.10
    åıijçĶŁåľ¨
    0.10
    æĿ¥ä¸´
    0.10
    çģ¾éļ¾
    0.10
    Activations Density 0.100%

    No Known Activations