© 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. 7099
    Prev
    Next
    INDEX
    Explanations

    antivirus software and OS security

    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
    çīĪ
    -0.10
    aks
    -0.10
    说ä¸įå®ļ
    -0.10
    è¾ķ
    -0.09
    ration
    -0.09
    ä¸Ģæłĭ
    -0.09
    /../
    -0.09
    ä¸Ģè§Ĵ
    -0.09
    åĪ©çĽĬ
    -0.09
    沦
    -0.09
    POSITIVE LOGITS
    æĬĬè¿Ļ个
    0.09
    éĿ¢ç§¯çº¦
    0.08
    é£İæļ´
    0.08
    æľ
    0.08
     мало
    0.08
    åĵĪå°Ķ
    0.08
    æ½¢
    0.08
    æݪæĸ½
    0.08
    urray
    0.08
     Cro
    0.08
    Activations Density 0.029%

    No Known Activations