© 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. 16703
    Prev
    Next
    INDEX
    Explanations

    love and relationships

    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
     Spare
    -0.09
    تش
    -0.09
    locate
    -0.08
    æħİ
    -0.08
     Dynam
    -0.08
     spare
    -0.08
    æīĪ
    -0.08
    èĬĿ麻
    -0.08
    åIJİåı°
    -0.08
    .asc
    -0.08
    POSITIVE LOGITS
    缸çĪ±
    0.14
    æľĢçĪ±
    0.12
    家人
    0.12
    çĪ±
    0.11
    ä¾Ķ
    0.11
     loved
    0.11
    çĪ±ä½ł
    0.10
    çĪ±äºº
    0.10
    æĦĽ
    0.10
    eneg
    0.10
    Activations Density 0.035%

    No Known Activations