© 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. 10287
    Prev
    Next
    INDEX
    Explanations

    related to petition or signature

    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
    形象
    -0.10
    æł·åŃIJ
    -0.09
     Pratt
    -0.08
    ibre
    -0.08
    é»ijæļĹ
    -0.08
    unist
    -0.08
     каÑĩеÑģÑĤв
    -0.08
    åıªçŁ¥éģĵ
    -0.08
    ä¹ħ
    -0.08
    åłķ
    -0.08
    POSITIVE LOGITS
     petition
    0.11
    æĶ¶éĽĨ
    0.11
     Pet
    0.10
    èĢĮæĪIJ
    0.10
    Pet
    0.10
    èģļä¼ļ
    0.10
    æıIJè®®
    0.10
     petitions
    0.09
    éĢģæĿ¥
    0.09
    æĺĬ
    0.09
    Activations Density 0.051%

    No Known Activations