© 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. 38973
    Prev
    Next
    INDEX
    Explanations

    stock market and exchange

    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
    ance
    -0.14
    ãģ£ãģįãĤĬ
    -0.13
     dÃłng
    -0.10
    æľµ
    -0.10
    	TokenName
    -0.10
    rors
    -0.10
    ugar
    -0.10
    ìĤ¬íķŃ
    -0.10
    ãģıãĤĮ
    -0.09
    ÑģÑĤанов
    -0.09
    POSITIVE LOGITS
    pile
    0.18
    smith
    0.14
    manship
    0.13
    side
    0.12
    holders
    0.12
    iest
    0.12
    yard
    0.12
    ery
    0.10
    tober
    0.10
    yards
    0.10
    Activations Density 0.017%

    No Known Activations