© 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. 58469
    Prev
    Next
    INDEX
    Explanations

    to maintain, publish, gain, expand

    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
    æŃ£å¸¸ä½¿çĶ¨
    -0.09
    alus
    -0.08
    éģ¿
    -0.08
    .normal
    -0.08
    çĬĬ
    -0.08
    ä¹Łæľīå¾Īå¤ļ
    -0.08
    é«¡
    -0.08
    好å¤Ħ
    -0.08
    ifiers
    -0.08
    prene
    -0.08
    POSITIVE LOGITS
    æıIJä¾Ľä¼ĺè´¨
    0.11
    èĩ´åĬĽäºİ
    0.10
    åĬª
    0.10
    åĬŀ好
    0.10
    宣è¨Ģ
    0.09
    å®ĹæŨ
    0.09
    åĬŀ
    0.09
    ÑĢай
    0.09
    isz
    0.09
    æĮ¯åħ´
    0.09
    Activations Density 0.181%

    No Known Activations