© 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. 10355
    Prev
    Next
    INDEX
    Explanations

    growth factor

    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
    ä¸ĢçĶŁ
    -0.10
    平常
    -0.09
    妹åŃIJ
    -0.09
    该游æĪı
    -0.09
     gener
    -0.09
    交代
    -0.09
     leve
    -0.09
    åĽĽå¤Ħ
    -0.08
    çIJ´
    -0.08
    wine
    -0.08
    POSITIVE LOGITS
    åķ¼
    0.11
    çļ±
    0.09
     اÙĦبر
    0.09
    æīĵå·¥
    0.08
    æ»ĭ
    0.08
     Carl
    0.08
    æķijæĬ¤
    0.08
    æ¯Ķ
    0.08
     Composition
    0.08
     Corm
    0.08
    Activations Density 0.205%

    No Known Activations