© 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. 8944
    Prev
    Next
    INDEX
    Explanations

    exoplanets and moons' activity

    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
    è¿ĺ羣
    -0.09
    æĽ³
    -0.09
    hips
    -0.09
    èĢĹ
    -0.09
    èĪ¬
    -0.08
    éĽĨä½ĵ
    -0.08
    uze
    -0.08
    å·¥å§Ķ
    -0.08
    çĮ¶
    -0.08
    cular
    -0.08
    POSITIVE LOGITS
    座
    0.09
    æ´»ä¸ĭåİ»
    0.09
    ç²¾è£ħ
    0.09
     permanently
    0.09
    çĴIJ
    0.08
    澡
    0.08
    温æ³ī
    0.08
    HAM
    0.08
    chin
    0.08
    æħĪ
    0.08
    Activations Density 0.049%

    No Known Activations