© 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. 21698
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

    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
    alam
    -0.10
    èĥŃ
    -0.10
     Millionen
    -0.09
     millions
    -0.09
     воп
    -0.09
    èĨı
    -0.08
    иÑĢов
    -0.08
    æ·±çŁ¥
    -0.08
    æºIJæºIJ
    -0.08
    宫殿
    -0.08
    POSITIVE LOGITS
     dozen
    0.09
    cai
    0.09
     اÙĦÙĪاØŃد
    0.08
    inals
    0.08
    ä»·éĴ±
    0.08
    çIJĥ
    0.08
    æĸ°äº§åĵģ
    0.08
    pector
    0.08
    åĪ
    0.07
    olg
    0.07
    Activations Density 0.019%

    No Known Activations