© 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. 36996
    Prev
    Next
    INDEX
    Explanations

    Marx(-ists), Rand, Lovecraft, authors

    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
    æīĵçł´äºĨ
    -0.09
    å²±
    -0.09
    å·¥å§Ķ
    -0.09
    é£ĺ
    -0.08
    GRAM
    -0.08
     Rao
    -0.08
    èĭŁ
    -0.08
    çĦ¶
    -0.08
    akter
    -0.08
    åĩºåĩ»
    -0.08
    POSITIVE LOGITS
    溥
    0.12
    eping
    0.11
    ting
    0.10
    ä¸ŃåĽ½çī¹èī²
    0.09
    aug
    0.09
    æµĴ
    0.08
     aug
    0.08
    强åĬ¿
    0.08
     Lup
    0.08
    ׼׳
    0.08
    Activations Density 0.001%

    No Known Activations