© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9185
    Prev
    Next
    INDEX
    Explanations

    naturally

    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
    å®ŀéĻħä¸Ĭæĺ¯
    -0.09
    çī¹æĦı
    -0.09
    éľİ
    -0.09
    avic
    -0.08
    åħ¬çĦ¶
    -0.08
    æѤåĪ»
    -0.08
    è¿Ŀ
    -0.08
    Lite
    -0.08
    oa
    -0.08
    åĪ°å¤Ħ
    -0.08
    POSITIVE LOGITS
    eer
    0.11
    çĦ¶æĺ¯
    0.11
     unsur
    0.10
    aturally
    0.10
    ç¥ĵ
    0.10
     grav
    0.09
     Naturally
    0.09
    coon
    0.09
    ä½łæĥ³
    0.09
    éĴ³
    0.09
    Activations Density 0.009%

    No Known Activations