© 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. 54003
    Prev
    Next
    INDEX
    Explanations

    no success

    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
    ä¸ĭä¸Ģ代
    -0.10
    è¦ģçŁ¥éģĵ
    -0.10
    epam
    -0.10
    ä½ĵè´´
    -0.09
    .metamodel
    -0.09
    PLIC
    -0.08
    uby
    -0.08
    Ars
    -0.08
    æīĵæī®
    -0.08
    åŃIJå¼¹
    -0.08
    POSITIVE LOGITS
     success
    0.24
    æĪIJåĬŁ
    0.21
    æĪIJåĬŁçļĦ
    0.20
    success
    0.18
     Success
    0.18
    Success
    0.17
     successes
    0.17
    æĪIJåĬŁçİĩ
    0.17
    çļĦæĪIJåĬŁ
    0.17
     ÑĥÑģпеÑħ
    0.16
    Activations Density 0.092%

    No Known Activations