© 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. 49682
    Prev
    Next
    INDEX
    Explanations

    accomplishments and impressive achievements

    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
    åıªä¼ļ
    -0.10
    æł¼
    -0.09
     cue
    -0.09
    ä»ĸä¼ļ
    -0.09
    åIJįæ°Ķ
    -0.09
    éĨį
    -0.09
    hoff
    -0.08
    æĹłåĬ©
    -0.08
    erton
    -0.08
    åħ¸åŀĭçļĦ
    -0.08
    POSITIVE LOGITS
    ä¸įæĺĵ
    0.12
    çļĦæĪIJ绩
    0.11
    çĶ¸
    0.10
    è¦ģçŁ¥éģĵ
    0.10
     Accom
    0.10
    ä¸į容æĺĵ
    0.10
    åħĭæľį
    0.09
     accomplishments
    0.09
    ä¸ļ绩
    0.09
    åłªç§°
    0.09
    Activations Density 0.049%

    No Known Activations