© 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. 17268
    Prev
    Next
    INDEX
    Explanations

    shipping or delivery destinations

    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
    æ©¡
    -0.10
    çķİ
    -0.09
    LR
    -0.09
     Fet
    -0.09
    æĭį
    -0.09
    èݺ
    -0.08
    æIJ¦
    -0.08
    说åĩº
    -0.08
    1
    -0.08
     Employ
    -0.08
    POSITIVE LOGITS
    çĸı
    0.12
    æıIJéĹ®
    0.10
    สà¸ĩ
    0.10
    èĬĤèĥ½
    0.09
    èĺħ
    0.09
    è¡¥é½IJ
    0.09
    éĨª
    0.09
    æ¶Īè´¹èĢħ
    0.09
     abb
    0.09
    æĶ¾å®½
    0.09
    Activations Density 0.013%

    No Known Activations