© 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. 37913
    Prev
    Next
    INDEX
    Explanations

    top 10 lists

    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
    _PG
    -0.09
     Alv
    -0.08
    åįµ
    -0.08
    ä¹Łæĺ¯ä¸Ģ个
    -0.08
     oval
    -0.08
    ç¦Ħ
    -0.08
    ä¸»åľº
    -0.08
    _DECLS
    -0.08
     Mun
    -0.08
    æĢ»éĿ¢ç§¯
    -0.08
    POSITIVE LOGITS
    çĭ¬è§Ĵ
    0.11
     ways
    0.11
    æĭĵ
    0.10
    åįģæĿ¡
    0.10
    Lite
    0.09
    æĽĿ
    0.09
    çIJĨçĶ±
    0.09
    è·ŁçĿĢ
    0.09
    涧
    0.09
    æ´¼
    0.09
    Activations Density 0.104%

    No Known Activations