© 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. 54443
    Prev
    Next
    INDEX
    Explanations

    events causing destruction or damage

    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
    éºĴ
    -0.11
     تÙĤدÙĬ
    -0.10
    æĿ¼
    -0.09
    ç¾Ķ
    -0.09
    .addAction
    -0.09
    éĢĤåºĶ
    -0.09
    åı¯èĥ½åĩºçİ°
    -0.09
    åĿ³
    -0.09
    åı¯ä»¥èİ·å¾Ĺ
    -0.09
    .actions
    -0.09
    POSITIVE LOGITS
    æ³°å·ŀ
    0.09
    æī¹éĩı
    0.08
    è¹Ĥ
    0.08
    å¼¹
    0.08
     Tale
    0.08
    æĥŁ
    0.08
    使å¾Ĺ
    0.08
    leh
    0.08
    loo
    0.08
    3
    0.08
    Activations Density 0.088%

    No Known Activations