© 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. 12232
    Prev
    Next
    INDEX
    Explanations

    up-and-coming, startup, new, unknown

    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
    é©»
    -0.11
    æijĬ
    -0.10
     Stall
    -0.09
     stall
    -0.09
    è°´
    -0.09
    çĽĺçĤ¹
    -0.08
    åŃ£
    -0.08
    ष
    -0.08
    onica
    -0.08
    _hyper
    -0.08
    POSITIVE LOGITS
    å¹´è½»çļĦ
    0.19
    è¾Ī
    0.18
    å¹´è½»
    0.18
     younger
    0.16
    æĸ°äºº
    0.15
    å¹´è¼ķ
    0.14
    年轻人
    0.14
     young
    0.14
     new
    0.13
     молод
    0.13
    Activations Density 0.087%

    No Known Activations