© 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. 61857
    Prev
    Next
    INDEX
    Explanations

    your email inbox

    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
    rial
    -0.09
    è¯Ħè®®
    -0.09
     Irving
    -0.09
    åIJŀ
    -0.09
     caravan
    -0.09
    agra
    -0.08
    ELS
    -0.08
    replacement
    -0.08
    oton
    -0.08
     cords
    -0.08
    POSITIVE LOGITS
    èIJ½åľ¨
    0.12
    åľ¨æĪijçļĦ
    0.11
    åĩºçİ°åľ¨
    0.10
    åľ¨ä»ĸçļĦ
    0.10
    æĤ¨çļĦ
    0.10
    éĢģåĪ°
    0.10
    éĤĪ
    0.09
    忽
    0.09
    驳
    0.09
    æĥ´
    0.09
    Activations Density 0.098%

    No Known Activations