© 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. 35821
    Prev
    Next
    INDEX
    Explanations

    hospitals and universities

    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
    xis
    -0.10
    iset
    -0.09
    vell
    -0.09
    jes
    -0.09
    ty
    -0.09
    å·¦åı³
    -0.09
    pyx
    -0.09
    æĭĪ
    -0.09
    èµ·éĩįæľº
    -0.09
    交éĢļå·¥åħ·
    -0.09
    POSITIVE LOGITS
    æįĭ
    0.09
    æł¹æľ¬ä¸į
    0.09
    åijĺ
    0.09
     DAM
    0.08
    害ç¾ŀ
    0.08
     dam
    0.08
    ç½ijæ°ij
    0.08
    coal
    0.08
    æĹıèĩªæ²»
    0.08
    积累äºĨ
    0.08
    Activations Density 0.010%

    No Known Activations