© 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. 49738
    Prev
    Next
    INDEX
    Explanations

    Bashar al-Assad

    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
    enate
    -0.09
    quÃŃ
    -0.09
    UTO
    -0.08
    çĶŁçī©åѦ
    -0.08
    å¹²èĦĨ
    -0.08
    éĹ¾
    -0.08
    å½ĵæĪIJ
    -0.08
     Bounds
    -0.08
    åĮĻ
    -0.08
    éĿĴæĺ¥
    -0.08
    POSITIVE LOGITS
    æī§æĶ¿
    0.09
    赶
    0.09
    æ´¾åĩº
    0.09
    ТÐķ
    0.09
    ipe
    0.08
    åıįèħIJåĢ¡å»ī
    0.08
    èĮ¬
    0.08
    æ´¾éģ£
    0.08
    åĴĮä»ĸçļĦ
    0.08
    æĢ»çIJĨ
    0.08
    Activations Density 0.044%

    No Known Activations