© 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. 1716
    Prev
    Next
    INDEX
    Explanations

    how to instructions

    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
    èµĭäºĪ
    -0.10
    awan
    -0.09
    ered
    -0.09
    容å¿į
    -0.09
    çĽijè§Ĩ
    -0.08
    krä
    -0.08
    渲æŁĵ
    -0.08
    nowrap
    -0.08
    عد
    -0.08
     pret
    -0.08
    POSITIVE LOGITS
    èģĶç³»æĸ¹å¼ı
    0.13
    æŃ¥éª¤
    0.12
    éĢĶå¾Ħ
    0.12
    å¦Ĥä½ķåİ»
    0.11
    åIJİç»Ń
    0.10
     steps
    0.10
    èİ·å¾ĹæĽ´å¤ļ
    0.10
    æĸ¹æ³ķ
    0.10
    ç´¢åıĸ
    0.09
    请èģĶç³»
    0.09
    Activations Density 0.103%

    No Known Activations