© 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. 35628
    Prev
    Next
    INDEX
    Explanations

    amnesty waivers and executive decisions

    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
    ÙĦاÙħ
    -0.10
    gs
    -0.09
    ä¿Ŀé²ľ
    -0.09
    جÙĬÙĦ
    -0.08
    WEST
    -0.08
    è¿ħçĮĽ
    -0.08
    çĦļ
    -0.08
    åĮ¿åIJį
    -0.08
     ve
    -0.08
    packing
    -0.08
    POSITIVE LOGITS
    赦
    0.20
     amnesty
    0.12
    æĶ¾è¿ĩ
    0.10
    主åħ¬
    0.10
    宥
    0.10
    宽
    0.10
    ä¼ĺæĥł
    0.10
    å¸ĮæľĽèĥ½å¤Ł
    0.09
    _Release
    0.09
    积
    0.09
    Activations Density 0.105%

    No Known Activations