© 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. 51118
    Prev
    Next
    INDEX
    Explanations

    university names and locations

    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
    éĽĨä½ĵç»ıæµİ
    -0.09
    anje
    -0.09
    æĥłæ°ij
    -0.09
    è¿ŀè¿ŀ
    -0.09
    çīĩåĪ»
    -0.08
    ä»ĸä¼ļ
    -0.08
    èĬ«
    -0.08
     nghè
    -0.08
    ç»Ĩç»Ĩ
    -0.08
    ä¹Łæĺ¯ä¸Ģç§į
    -0.08
    POSITIVE LOGITS
    èĦ±èIJ½
    0.08
    åĸī
    0.08
    æŃª
    0.08
    æĹłç§ģ
    0.08
    çĥŃéĹ¹
    0.08
     equally
    0.08
    çīĻ
    0.08
    å¹´ä¹ĭ
    0.08
    duk
    0.08
    WX
    0.07
    Activations Density 0.011%

    No Known Activations