© 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. 49442
    Prev
    Next
    INDEX
    Explanations

    served acame withshare dishdisplay dessert

    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
    æĺĤ
    -0.10
    ç³Ļ
    -0.09
    é¢Ŀ
    -0.09
    inke
    -0.09
    jang
    -0.09
    åģ¥
    -0.09
    éĶŃ
    -0.09
    åĴĤ
    -0.09
    åįķåħĥ
    -0.09
    .functional
    -0.09
    POSITIVE LOGITS
    åľĥ
    0.10
    主åĬ¨
    0.09
    éĢģåĪ°
    0.09
    ä¿Ŀ温
    0.09
    åIJį人
    0.09
    .cid
    0.08
    å¾ģæ±ĤæĦıè§ģ
    0.08
    主åĭķ
    0.08
    éĢģ
    0.08
    åı²è¯Ĺ
    0.08
    Activations Density 0.021%

    No Known Activations