© 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. 57625
    Prev
    Next
    INDEX
    Explanations

    Stella D'oro, Quorn products

    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
    èĥ¡åŃIJ
    -0.09
     Cloth
    -0.09
    çıŀ
    -0.09
    vere
    -0.09
    atar
    -0.09
    æ°
    -0.09
    cent
    -0.09
    çıłå®Ŀ
    -0.08
    å¼Łå¼Ł
    -0.08
    mq
    -0.08
    POSITIVE LOGITS
    é©¿
    0.10
    管è¾ĸ
    0.10
    åĴĮåľ°åĮº
    0.09
    жÑĥ
    0.09
     pure
    0.08
     UNUSED
    0.08
    纯
    0.08
    éĹ»
    0.08
     co
    0.08
     nomin
    0.08
    Activations Density 0.023%

    No Known Activations