© 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. 58583
    Prev
    Next
    INDEX
    Explanations

    financial protection bureau

    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
    -main
    -0.08
     crem
    -0.08
    Recipient
    -0.08
    çĩĥ
    -0.08
     Operational
    -0.08
    odata
    -0.08
     adam
    -0.08
    alon
    -0.08
     receiving
    -0.08
     Bowie
    -0.08
    POSITIVE LOGITS
    æĪIJç«ĭäºİ
    0.09
    ä¸Ģå¥Ĺ
    0.09
    -Russian
    0.09
    æ±²
    0.09
    ä¹ĸ
    0.09
    æ·¦
    0.09
    å¤
    0.09
    ãĥ¡ãĥ³ãĥĪ
    0.09
    ensburg
    0.08
    hc
    0.08
    Activations Density 0.004%

    No Known Activations