© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9526
    Prev
    Next
    INDEX
    Explanations

    of which/whom

    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
    Ñģка
    -0.10
    .asp
    -0.09
    bez
    -0.09
    è·ĥ
    -0.09
     اÙĦعب
    -0.09
    è¦ģçľĭ
    -0.08
    å®īåħ¨æĢ§
    -0.08
    æµĨ
    -0.08
     اÙĦشر
    -0.08
    ä½Ĩæĺ¯å¯¹äºİ
    -0.08
    POSITIVE LOGITS
     коÑĤоÑĢÑĭÑħ
    0.10
     which
    0.10
    æĪijèĩªå·±
    0.09
    éĥ½çŁ¥éģĵ
    0.09
     cui
    0.09
    åħ¶ä¸Ń
    0.08
     коÑĤоÑĢой
    0.08
    æĪijçŁ¥éģĵ
    0.08
    æĦŁäºº
    0.08
    untime
    0.08
    Activations Density 0.068%

    No Known Activations