© 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. 56617
    Prev
    Next
    INDEX
    Explanations

    Boko Haram

    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
    麻çĥ¦
    -0.11
    æ¿Ģ
    -0.10
    Ñĩе
    -0.09
    edList
    -0.09
    äºİæĺ¯æĪij
    -0.09
    LAG
    -0.08
    åīįèĢħ
    -0.08
    羯
    -0.08
     trouble
    -0.08
    ого
    -0.08
    POSITIVE LOGITS
    åĵĤ
    0.10
    窥
    0.09
    ä½ıäºĨ
    0.09
    (Build
    0.09
    ะ
    0.09
    APON
    0.09
    对éĿ¢
    0.08
    å¾Ĺä½ı
    0.08
    åł
    0.08
    æ»ļçIJĥ
    0.08
    Activations Density 0.023%

    No Known Activations