© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8743
    Prev
    Next
    INDEX
    Explanations

    budgetary reductions and funding constraints

    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
    红åĪ©
    -0.10
    éŁŃ
    -0.09
    обÑĭ
    -0.09
    åģľçīĮ
    -0.09
    ä¸Ģ身
    -0.09
    _lex
    -0.08
     Rudd
    -0.08
     VÅ©
    -0.08
    ç»ı纪人
    -0.08
    åĩºåľº
    -0.08
    POSITIVE LOGITS
    _budget
    0.10
    ror
    0.09
    åīĬåĩı
    0.09
    Plug
    0.09
    æ¯ıå¹´
    0.09
    é¢Ħç®Ĺ
    0.09
     Plug
    0.09
    itsu
    0.08
    çIJĨçͱ
    0.08
    对åħ¶
    0.08
    Activations Density 0.042%

    No Known Activations