© 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. 35587
    Prev
    Next
    INDEX
    Explanations

    thousands of

    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
    夷
    -0.09
    æŁIJç§įç¨ĭ度
    -0.08
    çģ«çĥ§
    -0.08
    flix
    -0.08
    åįģ足
    -0.08
    antu
    -0.08
    finder
    -0.08
     sque
    -0.07
    yster
    -0.07
    äºĽä»Ģä¹Ī
    -0.07
    POSITIVE LOGITS
    ths
    0.11
    aire
    0.10
    ä¸ªå·¥ä½ľ
    0.10
     ÙĦÙĥرة
    0.10
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.10
    ìĶ©
    0.10
    çĶļèĩ³æĺ¯
    0.09
    emente
    0.09
    åĩłçĻ¾
    0.09
    ple
    0.09
    Activations Density 0.022%

    No Known Activations