© 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. 63696
    Prev
    Next
    INDEX
    Explanations

    everyday topics and thoughts

    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
    دا
    -0.08
    æĺ¯ä»Ģä¹Īåij¢
    -0.08
    é£ĵ
    -0.07
    æ¼Ń
    -0.07
    å·¥ä½ľå²Ĺä½į
    -0.07
    ied
    -0.07
    ile
    -0.07
    ç¿ķ
    -0.07
    æĮ¯
    -0.07
    ç§ĭ天
    -0.07
    POSITIVE LOGITS
    æ¯ıåij¨
    0.10
    çĥŃçĤ¹
    0.10
    çī¹æ´¾
    0.10
    çĭ¬å®¶
    0.09
    æ¯ıæĹ¥ç»ıæµİ
    0.09
    ÑģÑĤÑĭ
    0.09
    å½ĵ天
    0.09
    inheritdoc
    0.09
    æķıéĶIJ
    0.09
    åīįä¸Ģ天
    0.09
    Activations Density 0.114%

    No Known Activations