© 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. 57383
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and decision bodies

    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
    ataka
    -0.10
    iest
    -0.10
    burger
    -0.09
    è¿ĩ硬
    -0.09
    é«ĺåĵģè´¨
    -0.09
    Ź
    -0.09
    èĤ¢
    -0.08
     обÑĬ
    -0.08
    åĨ¤
    -0.08
    åĪijäºĭ
    -0.08
    POSITIVE LOGITS
    çĶŁçĶŁ
    0.10
    æĩĭ
    0.10
    æ·¦
    0.09
    airs
    0.08
    室
    0.08
    失åĪ©
    0.08
    èħ¾é£ŀ
    0.08
    çĪ¿
    0.08
    çĭİ
    0.08
    çļĦéĩįçĤ¹
    0.08
    Activations Density 0.013%

    No Known Activations