© 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. 51249
    Prev
    Next
    INDEX
    Explanations

    decree or order issued by government

    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
    æĮĿ
    -0.10
    utow
    -0.09
    çĶ³æĬ¥
    -0.09
    iasco
    -0.08
    ä¸įåıĹ
    -0.08
    ä¿Ĥ
    -0.08
    å§ĵ
    -0.08
    .Highlight
    -0.08
    çºłçº·
    -0.08
    éĢıè§Ĩ
    -0.08
    POSITIVE LOGITS
    åij½ä»¤
    0.21
    ä¸ĭè¾¾
    0.19
    ä¸ĭ令
    0.17
    æĮĩ令
    0.16
    ä¸ĭåıij
    0.16
    é¢ģåıij
    0.15
    åIJ©åĴIJ
    0.14
    åıijåĩº
    0.14
    é¢ģå¸ĥ
    0.14
    æķķ
    0.13
    Activations Density 0.111%

    No Known Activations