© 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. 51317
    Prev
    Next
    INDEX
    Explanations

    social media buzz and packed places

    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
    .easy
    -0.11
    _OBS
    -0.10
    该游æĪı
    -0.09
    ä¸ŃåĽ½å¤§éĻĨ
    -0.09
    对èĩªå·±çļĦ
    -0.09
    _CRITICAL
    -0.09
    带走
    -0.09
    åĩºæĿ¥çļĦ
    -0.08
    åľ¨åĽ½åĨħ
    -0.08
    æĸ¹éĿ¢çļĦ
    -0.08
    POSITIVE LOGITS
    ä¸Ģçīĩ
    0.11
     оÑĩеÑĢед
    0.11
    éĿ¢çĽ®
    0.10
    åħħ满äºĨ
    0.10
    ä¸įçķĻ
    0.09
     Helena
    0.09
    æĬ«
    0.09
     wk
    0.08
    ä¸įåIJĮç¨ĭ度
    0.08
    onn
    0.08
    Activations Density 0.177%

    No Known Activations