© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37244
    Prev
    Next
    INDEX
    Explanations

    state-wide

    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
    à¸ģารà¸Ĺำ
    -0.10
    æĤ¬
    -0.09
    obox
    -0.09
    éĸ
    -0.09
    ader
    -0.09
    éŁ
    -0.09
    åı¶åŃIJ
    -0.09
    redicate
    -0.08
    flux
    -0.08
     Hayward
    -0.08
    POSITIVE LOGITS
    åħ¨ç¤¾ä¼ļ
    0.21
    æķ´ä¸ª
    0.19
    -wide
    0.18
    åħ¨åİ¿
    0.18
    åħ¨å¸Ĥ
    0.17
    æķ´ä¸ªäºº
    0.17
    åħ¨æł¡
    0.17
    åħ¨éķĩ
    0.17
    æķ´åĢĭ
    0.17
    åħ¨å±Ģ
    0.17
    Activations Density 0.146%

    No Known Activations