© 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. 39090
    Prev
    Next
    INDEX
    Explanations

    money, deposits, 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
    èµ°
    -0.09
    (expect
    -0.09
    æ·¡åĮĸ
    -0.09
    èĢIJ
    -0.09
    PO
    -0.08
    èĺij
    -0.08
    çĶŁæ´»çݯå¢ĥ
    -0.08
     Incorporated
    -0.08
     planned
    -0.08
     shaft
    -0.08
    POSITIVE LOGITS
    æĬ¼éĩij
    0.12
    æ£īèĬ±
    0.11
    ä¿Ŀè¯ģéĩij
    0.10
    èµĦæľ¬
    0.10
    èµĦéĩij
    0.10
    åij¨è½¬
    0.09
    å¤ĩçĶ¨
    0.09
    æįĨç»ij
    0.09
    èµĦè´¨
    0.09
    æľĢä½İ
    0.09
    Activations Density 0.055%

    No Known Activations