© 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. 53874
    Prev
    Next
    INDEX
    Explanations

    operation in or on

    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
     اÙĦØ«ÙĤ
    -0.08
    èĩªè¡Į
    -0.08
     loos
    -0.08
    och
    -0.08
    åħ¼
    -0.08
    æŃ»åİ»
    -0.08
     arity
    -0.08
    _ASC
    -0.08
     ÑģовеÑĢÑĪен
    -0.08
    深深çļĦ
    -0.08
    POSITIVE LOGITS
    æĬķåħ¥ä½¿çĶ¨
    0.14
    æŃ£å¼ı
    0.12
    æĬķ产
    0.12
    å¹´åĨħ
    0.12
    å®Įå·¥
    0.12
    éªĮæĶ¶
    0.11
    交ä»ĺ
    0.11
    竣工
    0.11
    ä¸Ĭ线
    0.11
    æłĩå¿ĹçĿĢ
    0.10
    Activations Density 0.128%

    No Known Activations