© 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. 27880
    Prev
    Next
    INDEX
    Explanations

    conflict and fights

    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
    .newaxis
    -0.10
    ä¸įå°½
    -0.09
    ään
    -0.09
    announce
    -0.09
    æĶ»åħĭ
    -0.09
    é©¿ç«Ļ
    -0.09
     sands
    -0.09
     announce
    -0.09
     Wahl
    -0.09
    ç¥ŀç§ĺ
    -0.08
    POSITIVE LOGITS
    æīĵæŀ¶
    0.15
    æ¿ĢçĥĪçļĦ
    0.14
    åIJµæŀ¶
    0.14
    è¡ħ
    0.13
    äºīåIJµ
    0.13
    åĨ²çªģ
    0.13
    äºī论
    0.13
    æ¿Ģ
    0.13
     confrontation
    0.12
    åIJµ
    0.12
    Activations Density 0.085%

    No Known Activations