© 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. 20873
    Prev
    Next
    INDEX
    Explanations

    quarterly dividend payout

    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
    blend
    -0.10
    åľ°æĿ¿
    -0.10
    交è°Ī
    -0.10
    被迫
    -0.09
    èĨı
    -0.09
    被éªĹ
    -0.09
    åĮ¡
    -0.09
    éĺ´å½±
    -0.09
    æ±ŁåĮº
    -0.08
    交æµģåIJĪä½ľ
    -0.08
    POSITIVE LOGITS
    å½ĵä¹ĭ
    0.10
    0
    0.10
    èĤ¡
    0.09
    iggins
    0.09
     rewards
    0.09
    éĢļåijĬ
    0.09
    4
    0.09
    6
    0.08
    8
    0.08
    èĮ§
    0.08
    Activations Density 0.011%

    No Known Activations