© 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. 59334
    Prev
    Next
    INDEX
    Explanations

    expresses belief or thought

    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
    å©¿
    -0.10
    åħ¥æĪ·
    -0.09
    çľ¼çĿĽ
    -0.09
    ç¨įç¨į
    -0.09
    æ¶īæ¡Ī
    -0.09
    íĺģ
    -0.09
    åĺİ
    -0.09
    ç©į
    -0.08
    çľ¼çľĭ
    -0.08
    强åĬ²
    -0.08
    POSITIVE LOGITS
    æ¸Ĭ
    0.09
    éĢIJ
    0.09
    缸åħ³æĶ¿çŃĸ
    0.08
     recip
    0.08
    æĬ¥éģĵ
    0.08
    LastError
    0.08
    类似çļĦ
    0.08
    CSI
    0.08
    æŁIJ个
    0.08
    åľ¨ç½ij绾ä¸Ĭ
    0.08
    Activations Density 0.146%

    No Known Activations