© 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. 53562
    Prev
    Next
    INDEX
    Explanations

    admission and entrance exams

    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
    enton
    -0.10
    æķĻæĿIJ
    -0.10
    å°ıåѦ
    -0.10
    æķĻæ¡Ī
    -0.09
    çīĮ
    -0.09
    械
    -0.09
    encies
    -0.09
    ä¼ijåģĩ
    -0.08
    éĴ§
    -0.08
     Horny
    -0.08
    POSITIVE LOGITS
    é«ĺèĢĥ
    0.13
    å½ķåıĸ
    0.11
     admission
    0.11
    çĩ§
    0.10
    éĻ¢
    0.09
     Admission
    0.09
     viá»ĩn
    0.09
    emb
    0.09
    å®ļåIJij
    0.09
    mb
    0.09
    Activations Density 0.076%

    No Known Activations