© 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. 29993
    Prev
    Next
    INDEX
    Explanations

    electroosmotic

    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
    çĽĺ
    -0.10
    磼
    -0.09
    ç¨³åĽº
    -0.09
    bourg
    -0.08
    纵
    -0.08
    еÑĢж
    -0.08
     Sey
    -0.08
    é«ĺæ°´å¹³
    -0.08
    ä¸įå½±åĵį
    -0.08
     Tit
    -0.08
    POSITIVE LOGITS
    æĶ¿åħļ
    0.10
    çķĢ
    0.09
    èĽĭçĻ½
    0.09
    弥漫
    0.09
    ç²®
    0.09
    ["@
    0.09
    æ§Ľ
    0.09
    ç»Ħç»ĩçĶŁæ´»
    0.09
    Weekly
    0.08
     Resize
    0.08
    Activations Density 0.444%

    No Known Activations