© 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. 63879
    Prev
    Next
    INDEX
    Explanations

    Chile

    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
    åĪ©
    -0.08
    ãģĬãģĭ
    -0.08
    -minded
    -0.08
    æĸ¯é¡¿
    -0.08
    æķħ乡
    -0.08
    åĩ¹
    -0.08
    ample
    -0.08
    éĴ¦
    -0.08
    é¥
    -0.08
    orte
    -0.08
    POSITIVE LOGITS
    ÙĬÙĪÙĨ
    0.12
    pery
    0.10
    izu
    0.10
    ä»ħä»ħ
    0.10
    onaut
    0.10
    pagesize
    0.10
    oner
    0.09
    inke
    0.09
    ä»ħä»ħæĺ¯
    0.09
    som
    0.09
    Activations Density 0.006%

    No Known Activations