© 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. 23011
    Prev
    Next
    INDEX
    Explanations

    compliance and requirements

    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
    åıĺæĽ´
    -0.09
    æĭ¿
    -0.09
    èµłéĢģ
    -0.09
    ÑĪÑĥ
    -0.08
    èĬ½
    -0.08
     Hamp
    -0.08
    mun
    -0.08
    æł½
    -0.08
    æĬĬæīĭ
    -0.08
    æĬ¹
    -0.08
    POSITIVE LOGITS
     compliance
    0.13
    åIJĪè§Ħ
    0.13
    éģµ
    0.13
    éģµå®Ī
    0.12
    鬧
    0.11
     Compliance
    0.11
    è¿Ŀåıį
    0.11
    è¿Ŀ
    0.11
    éĹ¹
    0.11
     comply
    0.10
    Activations Density 0.088%

    No Known Activations