© 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. 63660
    Prev
    Next
    INDEX
    Explanations

    Wild

    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
    çĻŀ
    -0.10
    æĭįåįĸ
    -0.09
    为äºĨéģ¿åħį
    -0.09
    åħ¥åľº
    -0.09
    èľ»
    -0.09
    æĢİä¹Īåı¯èĥ½
    -0.09
    说å¾Ĺ
    -0.09
     mest
    -0.09
    Tick
    -0.09
    æİĸ
    -0.08
    POSITIVE LOGITS
    åĮĻ
    0.10
     безоп
    0.09
    çļĦæĪIJ绩
    0.09
    elp
    0.08
    eto
    0.08
     Monter
    0.08
    ä¸ĭçļĦ
    0.08
     Plasma
    0.08
    icers
    0.08
    åľ¨å®¶
    0.08
    Activations Density 0.039%

    No Known Activations