© 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. 58997
    Prev
    Next
    INDEX
    Explanations

    years of

    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
    çļĦä¸ĢåĪĩ
    -0.10
    æĢ§å¼º
    -0.10
    è§ĩ
    -0.10
    ä»Ģä¹Īéĥ½
    -0.10
    ä¸ĢéĹª
    -0.10
    è¦ģè¿Ľä¸ĢæŃ¥
    -0.10
    åĴĮ个人
    -0.10
    apel
    -0.09
    æĬĹè®®
    -0.09
    趸
    -0.09
    POSITIVE LOGITS
    以èĩ³äºİ
    0.09
    åĮĹæĸ¹
    0.08
    以èĩ´
    0.08
     Achilles
    0.07
    lat
    0.07
    ritz
    0.07
    esimal
    0.07
    ordan
    0.07
    /or
    0.07
     Vend
    0.07
    Activations Density 0.007%

    No Known Activations