© 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. 19431
    Prev
    Next
    INDEX
    Explanations

    history and prior events

    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
    еÑĢж
    -0.10
    éħĮ
    -0.10
    éĴµ
    -0.10
     ÄijÃŃch
    -0.10
    èIJ½åľ¨
    -0.09
    éĽ¹
    -0.09
    çĮ·
    -0.09
    åĬ¡å®ŀ
    -0.09
    èµı
    -0.09
    æľīçļĦ人
    -0.09
    POSITIVE LOGITS
     history
    0.11
    æĺ¨å¤©
    0.11
    åľ¨æѤä¹ĭåīį
    0.10
    è¿ijæľŁ
    0.10
    æĺ¨æĻļ
    0.10
    æĽ¾åľ¨
    0.10
    å¹³æŶ
    0.09
    注æĦıåĪ°
    0.09
     prior
    0.09
    æľĢè¿ij
    0.09
    Activations Density 0.384%

    No Known Activations