© 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. 61100
    Prev
    Next
    INDEX
    Explanations

    reporter gene

    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
    åŁ¹åħ»åѦçĶŁ
    -0.10
     ÙĦدÙĬ
    -0.10
    以为
    -0.09
    ë²Į
    -0.09
    ä¸īçĤ¹
    -0.09
     Charg
    -0.09
    æĹ¥å¸¸
    -0.09
    alus
    -0.09
    æľºæ¢°è®¾å¤ĩ
    -0.09
    .coord
    -0.08
    POSITIVE LOGITS
     luc
    0.09
    追éļı
    0.09
    åĪ°å¤Ħ
    0.09
    ä½ĵç³»
    0.09
     tag
    0.09
     reporter
    0.09
    çŃīçĿĢ
    0.08
    æĮĩæľĽ
    0.08
    ãĤĴåħ¥ãĤĮ
    0.08
     marker
    0.08
    Activations Density 0.762%

    No Known Activations