© 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. 17126
    Prev
    Next
    INDEX
    Explanations

    death and murder of

    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
    æĭ¿æĿ¥
    -0.09
    åĩºçİ°éĹ®é¢ĺ
    -0.09
    好åĿı
    -0.09
    ä¹ĭåĬĽ
    -0.09
    ç³Ł
    -0.09
    æī¬å°ĺ
    -0.08
    å¹³æŶ
    -0.08
     опÑĭ
    -0.08
    ä¹ĭæĪĺ
    -0.08
     prere
    -0.08
    POSITIVE LOGITS
    æĤ²åī§
    0.11
    trag
    0.09
    æ»Ķ
    0.09
    åİŁåĽłæĺ¯
    0.08
    åĮĸå¦Ĩ
    0.08
    lap
    0.08
    æĤ²ä¼¤
    0.08
     whose
    0.08
    家å±ŀ
    0.08
    å¾Ĺä¸įåĪ°
    0.08
    Activations Density 0.091%

    No Known Activations