© 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. 31877
    Prev
    Next
    INDEX
    Explanations

    competition for positions

    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
    åħ¨äº§ä¸ļéĵ¾
    -0.09
     plagiar
    -0.09
     Jarvis
    -0.09
    çĵ¦
    -0.09
    åī¥å¤º
    -0.09
    åģ·
    -0.09
    ä»ĸèĩªå·±
    -0.09
    è¯Ŀåī§
    -0.08
    æłĢ
    -0.08
    å¿Į
    -0.08
    POSITIVE LOGITS
    æĹ¥è¶ĭ
    0.10
    åŤ
    0.09
    æ¿Ģ
    0.09
    å½¼æѤ
    0.09
     ultimately
    0.09
    究竣
    0.08
    ä¸ĭä¸Ģ代
    0.08
    åĪ°æľĢåIJİ
    0.08
    äºī缸
    0.08
    éĻįå¹ħ
    0.08
    Activations Density 0.050%

    No Known Activations