© 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. 37194
    Prev
    Next
    INDEX
    Explanations

    mining disasters and industry

    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
    ities
    -0.12
     Ñģобой
    -0.11
    ../../../
    -0.10
    teen
    -0.10
    管çIJĨæ°´å¹³
    -0.10
     chù
    -0.10
    uffs
    -0.10
     dÃłng
    -0.09
    cott
    -0.09
    ment
    -0.09
    POSITIVE LOGITS
    stead
    0.11
    yard
    0.10
    omial
    0.10
    audi
    0.09
    大æĪ·
    0.09
    ç¦ıå¾·
    0.09
    rig
    0.09
    egin
    0.09
    imizer
    0.08
    OrUpdate
    0.08
    Activations Density 0.028%

    No Known Activations