© 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. 22057
    Prev
    Next
    INDEX
    Explanations

    struggle against, focus on, specialisation in

    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
    渲
    -0.12
    çªĿ
    -0.10
    è¯Ħå®ļ
    -0.09
    读åIJİ
    -0.09
    æݩ饰
    -0.09
    -readable
    -0.09
    çı¥
    -0.09
     recycle
    -0.09
     Ñģмог
    -0.09
    ä¸İåIJ¦
    -0.08
    POSITIVE LOGITS
     mund
    0.10
    çıį
    0.09
    æĭ³
    0.09
    å°Ĩ继ç»Ń
    0.09
    伸æīĭ
    0.08
    缮çļĦåľ¨äºİ
    0.08
    æijĶ
    0.08
    æĹłè¾ľ
    0.08
    æŨ
    0.08
    æĢ»æĺ¯
    0.08
    Activations Density 0.102%

    No Known Activations