© 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. 20688
    Prev
    Next
    INDEX
    Explanations

    matters / matter

    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
    elpers
    -0.10
    èī¯
    -0.09
    raq
    -0.09
    ãĥĻãĤ¹ãĥĪ
    -0.09
    _ARCHIVE
    -0.09
    鸱
    -0.08
     Crosby
    -0.08
    iate
    -0.08
    иде
    -0.08
    æĿ¥åİĨ
    -0.08
    POSITIVE LOGITS
    æľĢéĩįè¦ģçļĦ
    0.12
    æľĢéĩįè¦ģ
    0.12
    éĩįçĤ¹
    0.11
    æľĢåħ³éĶ®
    0.10
    éĩįé»ŀ
    0.10
    çļĦéĩįçĤ¹
    0.10
    æīįæĺ¯çľŁæŃ£
    0.10
    åľ¨ä¹İ
    0.10
    è´¼
    0.10
    æĽ´éĩįè¦ģçļĦ
    0.09
    Activations Density 0.072%

    No Known Activations