© 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. 12421
    Prev
    Next
    INDEX
    Explanations

    evaporation and vaporization

    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
    amp
    -0.10
    à¸Ľà¸ı
    -0.10
    ä¼łéĹ»
    -0.10
    ì§ĵ
    -0.10
    UBLE
    -0.09
    OF
    -0.09
    éļ³
    -0.09
     cocks
    -0.09
    åĶĨ
    -0.08
    ãģĺ
    -0.08
    POSITIVE LOGITS
     lick
    0.10
    æİīäºĨ
    0.10
    /ion
    0.09
    충
    0.09
    lando
    0.09
    æĥ³å¿µ
    0.09
    äºŃ
    0.09
     Verm
    0.09
    -cond
    0.09
    è·ijäºĨ
    0.09
    Activations Density 0.026%

    No Known Activations