© 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. 21881
    Prev
    Next
    INDEX
    Explanations

    name followed by 's or number

    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
    ç§ijæĬĢèĤ¡ä»½
    -0.10
    è¢Ī
    -0.10
    诫
    -0.10
    oko
    -0.09
    ãģ®ä¸Ģ
    -0.09
    ç«ĸ
    -0.09
    coe
    -0.08
     Erotic
    -0.08
    itsu
    -0.08
    åİĭæĬij
    -0.08
    POSITIVE LOGITS
    æ³Ħ
    0.09
    oten
    0.09
    æľīæľŁ
    0.09
    åĽłä¸ºå¥¹
    0.09
    ÙĦس
    0.08
    éĻªä½ł
    0.08
    æ³»
    0.08
    adge
    0.08
    ä¼ļè®©ä½ł
    0.08
    é¡ĺ
    0.08
    Activations Density 0.035%

    No Known Activations