© 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. 40000
    Prev
    Next
    INDEX
    Explanations

    mass shooting victims

    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
    èĨı
    -0.10
    æ¹¾
    -0.10
    èĤ¡ä»½
    -0.09
    顾éĹ®
    -0.09
    个交æĺĵ
    -0.09
    èģĺ请
    -0.09
    åĨħåľ°
    -0.09
     Transmission
    -0.09
    à¸ĩ
    -0.09
    hud
    -0.08
    POSITIVE LOGITS
    æIJº
    0.10
    å³Ļ
    0.10
    ä½ķå¤Ħ
    0.09
    大éĿ¢ç§¯
    0.09
     bolt
    0.09
    éģıåĪ¶
    0.09
    å«Į
    0.09
     MASS
    0.09
     Campos
    0.09
    ave
    0.08
    Activations Density 0.131%

    No Known Activations