© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40331
    Prev
    Next
    INDEX
    Explanations

    dance music and performance

    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
    Negative Logits
    罩
    -0.13
    èĨ³
    -0.11
     Merkel
    -0.10
    åħ°
    -0.09
    å®ĺæĸ¹å¾®åįļ
    -0.09
    ç¼ĸåī§
    -0.09
    åĸŁ
    -0.09
    çĽ¸å£°
    -0.08
    -php
    -0.08
    è¯ĹæĦı
    -0.08
    POSITIVE LOGITS
    è·³èĪŀ
    0.12
    èĪŀè¹Ī
    0.11
    èĪŀ
    0.11
     dance
    0.10
    oppable
    0.10
    åĬ²
    0.10
     floor
    0.10
    åģ¥
    0.09
    åģ¥èº«
    0.09
    åĭģ
    0.09
    Activations Density 0.060%

    No Known Activations