© 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. 21841
    Prev
    Next
    INDEX
    Explanations

    sadness

    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
    orna
    -0.09
     Builders
    -0.09
    ç«¿
    -0.09
    æ¿Ģ
    -0.09
    çĤ¹åįĬ
    -0.08
    èļģ
    -0.08
    etur
    -0.08
    èĢĮä¸įæĺ¯
    -0.08
    åįĥæĸ¹çĻ¾è®¡
    -0.08
    åħ³éĶ®æŶåĪ»
    -0.08
    POSITIVE LOGITS
    ening
    0.10
    绪
    0.10
    æĺ¯çľŁçļĦ
    0.10
    wards
    0.09
    WARDS
    0.09
    ðŁĺ¢
    0.09
    çĹħæ¯ĴæĦŁæŁĵ
    0.09
    ç³Ĭæ¶Ĥ
    0.09
    æľĭåıĭ们对
    0.08
    hiro
    0.08
    Activations Density 0.013%

    No Known Activations