© 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. 2106
    Prev
    Next
    INDEX
    Explanations

    invention relates to apparatus

    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
    åľ¨èģĮ
    -0.10
    çľ·
    -0.09
    ç¬ĶèĢħ
    -0.09
    apos
    -0.08
    æľīå¾Īå¤ļ
    -0.08
    çĿĢéĩį
    -0.08
    ä¾ĿéĿł
    -0.08
    bor
    -0.08
    æĪijåĸľæ¬¢
    -0.08
    éĴ¦
    -0.08
    POSITIVE LOGITS
    åĪļæīį
    0.10
    å¼łåħĪçĶŁ
    0.10
    大æĸ¹
    0.09
    æĤ²è§Ĥ
    0.09
    è¿ŀ线
    0.09
    æ§İ
    0.09
    绪
    0.09
    è¦ģ说
    0.08
    åĮĹ京æŶéĹ´
    0.08
    åĬŁæķĪ
    0.08
    Activations Density 0.024%

    No Known Activations