© 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. 17472
    Prev
    Next
    INDEX
    Explanations

    coating or finish

    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
    æľŁåĨħ
    -0.11
    主ä½ĵ
    -0.10
    éĿ¡
    -0.10
    çĽĹ
    -0.09
    Injector
    -0.09
     priesthood
    -0.09
     SN
    -0.09
    еÑģÑģ
    -0.08
    åĪį
    -0.08
    伸
    -0.08
    POSITIVE LOGITS
    éĺ´
    0.09
    åĽŀåIJĪ
    0.09
    åĦ
    0.09
    çļĦå±ĢéĿ¢
    0.08
    åºĹ
    0.08
    _intf
    0.08
    代价
    0.08
    çļĦ好å¤Ħ
    0.08
    æ¾Ħ
    0.08
    dish
    0.08
    Activations Density 0.108%

    No Known Activations