© 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. 55444
    Prev
    Next
    INDEX
    Explanations

    what is 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
    ä¸Ģå®ļç¨ĭ度
    -0.09
    åĩºçĤī
    -0.08
     ÑĢежим
    -0.08
    åĪ©çĶ¨çİĩ
    -0.08
     McGregor
    -0.08
    èݲèĬ±
    -0.07
    åĩºçİ°åľ¨
    -0.07
    éĤł
    -0.07
    æŁIJç§įç¨ĭ度
    -0.07
    ior
    -0.07
    POSITIVE LOGITS
    åĨħå¹ķ
    0.10
    æĺ¯ä¸Ģ座
    0.10
    äºĨä¸Ģåı£
    0.10
    笺
    0.10
    çļĦåĨħ容
    0.09
    çļĦä¸Ģ款
    0.09
    raction
    0.09
     bè
    0.09
    entai
    0.09
    çļĦ身ä½ĵ
    0.09
    Activations Density 0.171%

    No Known Activations