© 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. 35288
    Prev
    Next
    INDEX
    Explanations

    fiscal results reported

    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
    俸
    -0.09
    æĹłåı¯
    -0.08
    æŃ£å½ĵ
    -0.08
    åıĤ
    -0.08
    ONS
    -0.08
    åĪ®
    -0.08
    åħ¬ç¤º
    -0.07
    å¾ĭ
    -0.07
     flav
    -0.07
     Nationals
    -0.07
    POSITIVE LOGITS
    åĩıåĢ¼
    0.10
    åł°
    0.09
    é¦ĸå¸Ń
    0.09
    æĤ¼
    0.09
    ç¹
    0.09
    管çIJĨå±Ĥ
    0.09
    ç½ij绾å®īåħ¨
    0.09
    æıIJæĮ¯
    0.09
    ç±»åĪ«
    0.09
    .namespace
    0.09
    Activations Density 0.079%

    No Known Activations