© 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. 50169
    Prev
    Next
    INDEX
    Explanations

    recurrence rate

    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
    olean
    -0.11
    çĥŁçģ«
    -0.10
    ç®ĹäºĨ
    -0.09
    ç²¾çĽĬæ±Ĥç²¾
    -0.09
    èĥ½ä½¿
    -0.09
    æĪ¾
    -0.09
    涩
    -0.09
    æĵİ
    -0.09
    æĢ¥å¿Ļ
    -0.09
    oley
    -0.08
    POSITIVE LOGITS
    å¤įåıij
    0.11
    å·©åĽº
    0.11
    åĨįçĶŁ
    0.10
    åıįå¼¹
    0.10
     recurrence
    0.10
     underlying
    0.09
    åIJĮç±»
    0.09
    åĨįçİ°
    0.09
    ä¸įä¹ħ
    0.09
    é¢Ħéĺ²
    0.09
    Activations Density 0.091%

    No Known Activations