© 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. 29779
    Prev
    Next
    INDEX
    Explanations

    air quality and breath

    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
    ãĥĮ
    -0.10
    åħ¨åijĺ
    -0.09
    åĬŁå¤«
    -0.09
    å°ıåŀĭ
    -0.09
    èĮĥ
    -0.09
    å®Ľ
    -0.09
    æĺĨ
    -0.08
    åĩŃ
    -0.08
    èľ¡
    -0.08
    麻çĹ¹
    -0.08
    POSITIVE LOGITS
    空æ°Ķ
    0.19
    空æ°Ķè´¨éĩı
    0.18
    空æ°Ķä¸Ń
    0.15
    åij¼åIJ¸
    0.14
     air
    0.13
     воздÑĥÑħ
    0.13
     breath
    0.13
    .air
    0.12
     respir
    0.12
    æ¸ħæĸ°
    0.12
    Activations Density 0.042%

    No Known Activations