© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21451
    Prev
    Next
    INDEX
    Explanations

    financial transactions and advances

    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
    åij¼
    -0.10
    ä¼°åĢ¼
    -0.09
    éĵŃè®°
    -0.09
     asc
    -0.08
    indi
    -0.08
    çijķçĸµ
    -0.08
    çªģ
    -0.08
    è´¹
    -0.08
    asc
    -0.08
     office
    -0.08
    POSITIVE LOGITS
    åıijæĶ¾
    0.16
    åĪ°è´¦
    0.12
    款项
    0.12
    éĴ±
    0.10
    èµĦéĩij
    0.10
     disb
    0.10
    phia
    0.10
    åĪ°ä½į
    0.10
    é¢Ĩåıĸ
    0.10
    енÑĮ
    0.09
    Activations Density 0.056%

    No Known Activations