© 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. 33174
    Prev
    Next
    INDEX
    Explanations

    tax relief and insurance policy

    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
     diá»ħn
    -0.08
    åķĸ
    -0.08
    strained
    -0.08
    æĬ»
    -0.08
    å¤ĸæĿ¥
    -0.08
    è´¨éĩı管çIJĨ
    -0.07
     reserves
    -0.07
    æľºèº«
    -0.07
    è¿Ļæī¹
    -0.07
    allee
    -0.07
    POSITIVE LOGITS
    unate
    0.10
    åIJĪæ³ķ
    0.10
    ç»Ħç»ĩçĶŁæ´»
    0.10
    оÑī
    0.10
    ãĤ§
    0.09
    ysz
    0.09
    æĩ
    0.09
     ترÙĥ
    0.09
    iswa
    0.09
    å°ĺ
    0.09
    Activations Density 0.099%

    No Known Activations