© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1226
    Prev
    Next
    INDEX
    Explanations

    stumbled on this

    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
    çŃIJ
    -0.09
    éĥ½çŁ¥éģĵ
    -0.09
    çĸĶ
    -0.09
    æīĭä¸ĭ
    -0.09
    ä¹ĭåĬ¿
    -0.08
    Spoiler
    -0.08
    è§Ī
    -0.08
    eration
    -0.08
    活泼
    -0.08
    æļ´
    -0.08
    POSITIVE LOGITS
    éĿŀ常åĸľæ¬¢
    0.10
    éĿŀ常好çļĦ
    0.10
    åķĨæľº
    0.09
    å¦Ļ
    0.09
    æ¯Ķè¾ĥ好
    0.09
    çİ°
    0.09
    ãĥĨãĥ³
    0.08
    å¯Įæ°ij
    0.08
    æĸ°çļĦ
    0.08
    DY
    0.08
    Activations Density 0.140%

    No Known Activations