© 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. 4764
    Prev
    Next
    INDEX
    Explanations

    eye feeling

    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
     пÑĥ
    -0.09
    èĿĩ
    -0.09
    èĸħ
    -0.09
    åĽºå®ļ
    -0.09
    åĭģ
    -0.09
    fel
    -0.09
    åĽºå®ļçļĦ
    -0.08
    ç²ĺ
    -0.08
    Emoji
    -0.08
    å³¥
    -0.08
    POSITIVE LOGITS
    åİ¥
    0.09
    æĢ»å±Ģ
    0.09
    aka
    0.09
     Gone
    0.09
    æĦŁåıĹåĪ°äºĨ
    0.08
    éĴ½
    0.08
    alen
    0.08
     Truth
    0.08
    /widget
    0.08
    æĸĩåŃĹ
    0.08
    Activations Density 0.001%

    No Known Activations