© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21044
    Prev
    Next
    INDEX
    Explanations

    massacre, rape, POWs, partition, pictures

    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
     дела
    -0.09
    èIJĮ
    -0.09
    åıijå±ķéĺ¶æ®µ
    -0.09
    æŦ
    -0.09
    sher
    -0.09
    è¹´
    -0.09
    çĹĴ
    -0.09
    èĮģ
    -0.09
     Borg
    -0.08
    èĽ°
    -0.08
    POSITIVE LOGITS
    èĩªåıij
    0.09
     kê
    0.09
    èĵ¬
    0.09
    éĢ¼
    0.09
    è¯ļ
    0.09
    ç¡®
    0.09
    inic
    0.08
    çķĻä¸ĭæĿ¥
    0.08
    çķĮ
    0.08
    .shtml
    0.08
    Activations Density 0.099%

    No Known Activations