© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50604
    Prev
    Next
    INDEX
    Explanations

    stand out / up; sets apart

    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
    umen
    -0.08
    à¸ĩ
    -0.08
    鬼
    -0.08
     alignment
    -0.08
    æĹħ
    -0.08
    线ä¸ĭ
    -0.08
    çıł
    -0.07
    äºŁ
    -0.07
    lasses
    -0.07
    ERN
    -0.07
    POSITIVE LOGITS
    èĦ±é¢ĸèĢĮåĩº
    0.11
    çªģåĩº
    0.10
    åī©ä¸ĭ
    0.10
     LSB
    0.10
    å±¹
    0.10
    æµĬ
    0.09
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.09
    çĭİ
    0.09
    åŃ°
    0.09
    sen
    0.09
    Activations Density 0.020%

    No Known Activations