© 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. 16883
    Prev
    Next
    INDEX
    Explanations

    percentage similarity

    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
    éªļ
    -0.10
    à¸ģำ
    -0.10
    маг
    -0.10
    è·»
    -0.10
    .inflate
    -0.10
    缺å¸Ń
    -0.10
    ê°ģ
    -0.09
     ì¤Ģ
    -0.09
    移交
    -0.09
    ä¼łæİĪ
    -0.09
    POSITIVE LOGITS
    çĽ¸ä¼¼
    0.17
     similarities
    0.17
     similarity
    0.16
     resemblance
    0.13
     resembl
    0.11
     resemble
    0.11
    缸éĢļ
    0.10
    åIJ»
    0.10
    åĢŁéī´
    0.09
    _similarity
    0.09
    Activations Density 0.301%

    No Known Activations