© 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. 38594
    Prev
    Next
    INDEX
    Explanations

    guidance and guidelines

    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
    utan
    -0.10
    æ¯ıä¸Ģ天
    -0.10
    pch
    -0.08
    ivel
    -0.08
    phin
    -0.08
    ä¸įç»ı
    -0.08
    æĸĹ
    -0.08
    å¿Ļç¢Į
    -0.08
    辫
    -0.08
     pure
    -0.08
    POSITIVE LOGITS
    æĮĩ导æĦıè§ģ
    0.18
    æĮĩå¼ķ
    0.17
    æĮĩåįĹ
    0.16
     guidelines
    0.15
     guideline
    0.14
    è§ĦèĮĥ
    0.13
    æĮĩ导
    0.13
    æĮĩ导ä¸ĭ
    0.13
     Guidelines
    0.13
    æĮĩå°İ
    0.12
    Activations Density 0.136%

    No Known Activations