© 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. 6248
    Prev
    Next
    INDEX
    Explanations

    court case identifiers

    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
    spl
    -0.09
    人æ°ij
    -0.08
    essions
    -0.08
    ession
    -0.08
    pressive
    -0.08
    è´«ç©·
    -0.08
    ume
    -0.08
    çĮ©
    -0.08
    ONA
    -0.08
    pig
    -0.07
    POSITIVE LOGITS
    羣çĪ±
    0.10
    åĪĨ级
    0.10
    鼶è·Ŀ离
    0.09
    æĪijçĪ±ä½ł
    0.09
    ä¸ŃæľŁ
    0.09
    碰åĪ°
    0.09
    .ServiceModel
    0.08
    à¸Ĺร
    0.08
     Unsure
    0.08
    åĪĨæł¡
    0.08
    Activations Density 0.035%

    No Known Activations