© 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. 54471
    Prev
    Next
    INDEX
    Explanations

    adhesion, fusion, attachment

    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
    çļĦ形象
    -0.09
    olv
    -0.09
    hole
    -0.09
    çĴĢçĴ¨
    -0.09
     Rack
    -0.09
    æ¼¾
    -0.08
    å°ıåŃIJ
    -0.08
     retire
    -0.08
    orsch
    -0.08
     reimb
    -0.08
    POSITIVE LOGITS
    ä½ıäºĨ
    0.13
    åľ¨ä¸Ģèµ·
    0.12
    ä¸įåĬ¨
    0.12
    каÑĢÑĤ
    0.10
    çī¢
    0.10
    éĻĦ
    0.10
    é»ı
    0.10
    ç²ĺ
    0.09
     liá»ģn
    0.09
    æģIJ
    0.09
    Activations Density 0.147%

    No Known Activations