© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23499
    Prev
    Next
    INDEX
    Explanations

    park & preserve names

    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
    ä¹ħ
    -0.09
    ressing
    -0.09
    æ±ĩ
    -0.09
    æ·¹
    -0.08
    cliffe
    -0.08
    åĮ¯
    -0.08
     Garrett
    -0.08
    eller
    -0.08
    çĭ¬ä¸ĢæĹłäºĮ
    -0.08
    宽容
    -0.08
    POSITIVE LOGITS
    主人
    0.09
    主人åħ¬
    0.09
    å³Ń
    0.09
    ç´¯äºĨ
    0.09
    å¨ĺ
    0.09
     Nack
    0.08
    饮éħĴ
    0.08
    izon
    0.08
     dividend
    0.08
    åħ¬çĽĬæĢ§
    0.08
    Activations Density 0.019%

    No Known Activations