© 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. 17592
    Prev
    Next
    INDEX
    Explanations

    reports, explains, explores, relives, looks, joins

    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
    笳
    -0.13
    ä¸įä¸ĭ
    -0.10
    丰满
    -0.09
    çĵ´
    -0.09
    èĥ½è¾¾åĪ°
    -0.09
    è¿Ļä¹Ī大
    -0.09
    è¡Įäºĭ
    -0.09
    ibble
    -0.09
    ä»Ģä¹Īæł·
    -0.09
    声æĺİ
    -0.08
    POSITIVE LOGITS
    æĬ¥éģĵ
    0.09
    å°ıå§IJå§IJ
    0.08
    mare
    0.08
    åĽŀæĬ¥
    0.08
    ForResult
    0.08
    主æĮģ
    0.08
    çĩļ
    0.08
    .addData
    0.08
    ä¸Ĭæµ·è¯ģåĪ¸
    0.08
     dra
    0.07
    Activations Density 0.073%

    No Known Activations