© 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. 21155
    Prev
    Next
    INDEX
    Explanations

    extract from

    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
     Lair
    -0.11
    é©·
    -0.10
    à¤ł
    -0.09
    ä¸įåħį
    -0.09
    éªħ
    -0.08
    äºĭæ¥Ń
    -0.08
    ä¿Ŀä½ı
    -0.08
    éĩįè¦ģæĦıä¹ī
    -0.08
    对å¤ĸ
    -0.08
    oney
    -0.08
    POSITIVE LOGITS
    çªĹ
    0.09
    OOM
    0.08
    çĬ¹å¦Ĥ
    0.08
    çªĹæĪ·
    0.08
    äºĴèģĶç½ij
    0.08
    çºł
    0.08
    èĦijæµ·
    0.08
     poo
    0.08
     khá»ıi
    0.08
     воÑĤ
    0.08
    Activations Density 0.139%

    No Known Activations