© 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. 1707
    Prev
    Next
    INDEX
    Explanations

    gaining knowledge or experience

    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
    塬
    -0.10
    elier
    -0.10
     segreg
    -0.09
    好åĥıæĺ¯
    -0.09
    æĴĩ
    -0.09
    inate
    -0.09
    åĨĴçĿĢ
    -0.09
    åij½ä¸Ń
    -0.09
    åij½
    -0.08
    æĢł
    -0.08
    POSITIVE LOGITS
    éĶ»çĤ¼
    0.21
    磨
    0.16
    éĶ¤
    0.16
    积累
    0.14
    积累äºĨ
    0.13
    åѦåĪ°
    0.13
    ç»ıéªĮåĢ¼
    0.13
     experience
    0.13
    å®ŀè·µç»ıéªĮ
    0.13
    ä½ĵä¼ļ
    0.12
    Activations Density 0.074%

    No Known Activations