© 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. 24252
    Prev
    Next
    INDEX
    Explanations

    biblical and historical names

    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
    çĬ¶åħĥ
    -0.10
    æĤ²è§Ĥ
    -0.10
    _pref
    -0.09
     OFFSET
    -0.09
    ä¸ĢçĤ¹çĤ¹
    -0.09
    .Standard
    -0.09
    å¤ĸåĽ´
    -0.09
    ÑĢом
    -0.09
     Hood
    -0.09
    exec
    -0.09
    POSITIVE LOGITS
    éĤij
    0.08
    ÙĬØ«
    0.08
    æ¯įæł¡
    0.08
    è´´åIJ§
    0.08
    æĩĤå¾Ĺ
    0.08
    ses
    0.08
    èĵĵ
    0.07
    andal
    0.07
    é«ĺ楼
    0.07
    BIN
    0.07
    Activations Density 0.022%

    No Known Activations