© 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. 7886
    Prev
    Next
    INDEX
    Explanations

    electricity generation or purchases

    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
    ä¸Ģæī¹
    -0.09
    æľ¬ç«Ļ
    -0.09
    æĢ§åij½
    -0.08
    åĴķ
    -0.08
    åį¿
    -0.08
    ä¸Ģç¬Ķ
    -0.08
    åı¸é©¬
    -0.08
     cá»Ń
    -0.08
    éĺ»æŃ¢
    -0.08
    西äºļ
    -0.08
    POSITIVE LOGITS
    æī¶
    0.09
    æİīèIJ½
    0.09
    å¸ĤåľºçļĦ
    0.09
     Ogre
    0.09
    awe
    0.09
    коÑģ
    0.09
    ãĥħ
    0.09
     ROUND
    0.08
    acad
    0.08
    /cards
    0.08
    Activations Density 0.040%

    No Known Activations