© 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. 31335
    Prev
    Next
    INDEX
    Explanations

    revised, designed, predecessor for

    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
    ertino
    -0.11
    ç¢Į
    -0.10
    ÑģÑĤолÑĮ
    -0.10
    çĥĤ
    -0.10
    çĻ¾åIJĪ
    -0.09
    丰
    -0.09
    åľ°æłĩ
    -0.09
    å°ı康
    -0.09
    инÑĦ
    -0.09
    åģ¥åħ¨
    -0.09
    POSITIVE LOGITS
    åĻ¨æĿIJ
    0.10
     Sport
    0.09
    è¿Ļ款
    0.09
    俱ä¹IJéĥ¨
    0.08
    posites
    0.08
    æīĭæĦŁ
    0.08
     adidas
    0.08
     Sports
    0.08
    è¿IJåĬ¨åijĺ
    0.08
    éħį
    0.08
    Activations Density 0.082%

    No Known Activations