© 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. 37373
    Prev
    Next
    INDEX
    Explanations

    defeat

    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
    -0.11
    ãģıãĤĭ
    -0.09
    imen
    -0.09
     behalf
    -0.09
    vin
    -0.09
    åŃ¦å®¶
    -0.08
    gel
    -0.08
    俳
    -0.08
    æ¬ºè´Ł
    -0.08
    éħİ
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.15
    ably
    0.12
    纵è§Ĥ
    0.11
    ively
    0.10
    л
    0.10
     localVar
    0.10
    æĺŁè¾°
    0.10
    ment
    0.09
    ess
    0.09
    iable
    0.09
    Activations Density 0.013%

    No Known Activations