© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51260
    Prev
    Next
    INDEX
    Explanations

    new year

    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
    è°ĭ
    -0.09
    mand
    -0.09
    idos
    -0.08
    arent
    -0.08
    åĪĨ离
    -0.08
    人äºĭ
    -0.08
    ä¸ŃéĢĶ
    -0.08
    ris
    -0.08
    ped
    -0.08
    夫人
    -0.08
    POSITIVE LOGITS
    èµĽåŃ£
    0.09
    çļĦåĪ°æĿ¥
    0.09
    è½®åĽŀ
    0.09
    çijķ
    0.09
    èµ·çĤ¹
    0.09
    ÑģÑĤи
    0.09
    Opera
    0.08
    åŃ¦æľŁ
    0.08
    ä¿¡èµĸ
    0.08
    é¹ĩ
    0.08
    Activations Density 0.061%

    No Known Activations