© 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. 8146
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of people or things

    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
     mag
    -0.09
    sth
    -0.09
    ä¸Ģæīĭ
    -0.09
    æ¼Ĩ
    -0.08
    åIJİçļĦ
    -0.08
     carr
    -0.08
    аÑĢÑĮ
    -0.08
    ÙĩÙĨ
    -0.08
    ä¸įè§ģ
    -0.08
    æľīèĥ½åĬĽ
    -0.08
    POSITIVE LOGITS
    å¤©çľŁ
    0.11
    åı¯çĪ±
    0.11
    è¢Ĵ
    0.10
    åŃij
    0.10
    earing
    0.10
    åı¯çĪ±çļĦ
    0.09
    éĢĹ
    0.09
    ovable
    0.09
    çijķ
    0.09
     Hatch
    0.09
    Activations Density 0.062%

    No Known Activations