© 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. 52508
    Prev
    Next
    INDEX
    Explanations

    chapter or section names

    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
     dress
    -0.09
     Dress
    -0.09
    æĬĬæĮģ
    -0.08
    çļĦçľ¼ç¥ŀ
    -0.08
    Coal
    -0.08
    ajar
    -0.08
    ä½ĵçİ°åĩº
    -0.08
    unya
    -0.08
    æ´¸
    -0.08
    glas
    -0.08
    POSITIVE LOGITS
    esk
    0.10
    Ñĥд
    0.09
    anches
    0.09
    åĴĮåľ°åĮº
    0.09
    blink
    0.09
    çĪĨ
    0.09
     Busy
    0.08
     darm
    0.08
    ansen
    0.08
    å°ī
    0.08
    Activations Density 0.008%

    No Known Activations