© 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. 8502
    Prev
    Next
    INDEX
    Explanations

    ecosystems and habitats

    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
    burgh
    -0.10
    麻çĹ¹
    -0.10
    éĶ£
    -0.09
    é¤ħ
    -0.09
    bud
    -0.09
    å¦ĤæĦı
    -0.08
     Streets
    -0.08
    æľµ
    -0.08
    çĥĪ
    -0.08
    elters
    -0.08
    POSITIVE LOGITS
     environments
    0.15
    çݯå¢ĥä¸Ń
    0.15
    çݯå¢ĥ
    0.14
    çĶŁæĢģç³»ç»Ł
    0.14
    çĶŁæĢģçݯå¢ĥ
    0.12
     habitats
    0.12
     môi
    0.11
     environment
    0.11
    çݯå¢ĥä¸ĭ
    0.11
     ecosystems
    0.11
    Activations Density 0.113%

    No Known Activations