© 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. 18367
    Prev
    Next
    INDEX
    Explanations

    death, cremation, service, grieving, education

    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
    ç³Ł
    -0.09
    ä¸Ĭ课
    -0.09
    .setAuto
    -0.09
    æĬµæĮ¡
    -0.08
     blur
    -0.08
    bang
    -0.08
    éĢ®
    -0.08
    éĴĿ
    -0.08
    aml
    -0.08
    HS
    -0.08
    POSITIVE LOGITS
    èij¬
    0.12
     crem
    0.11
    çĦļ
    0.10
    å¯Ħæīĺ
    0.10
     urn
    0.10
    æ®Ħ
    0.10
    çĽ¸äº²
    0.10
    仪å¼ı
    0.10
    urn
    0.09
    ç¼ħ
    0.09
    Activations Density 0.059%

    No Known Activations