© 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. 3918
    Prev
    Next
    INDEX
    Explanations

    reach or come to conclusions

    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
    åIJ¸åıĸ
    -0.09
    çĿ¦
    -0.09
    æŀ¢çº½
    -0.08
    lifetime
    -0.08
    CADE
    -0.08
    ä»ħ次
    -0.08
    andle
    -0.08
    åĬ³
    -0.08
    åŀ¦
    -0.08
     Whe
    -0.08
    POSITIVE LOGITS
    ç»ĵ论
    0.17
    å¾Ĺåĩº
    0.16
     conclusions
    0.13
     conclusion
    0.12
     arrive
    0.10
    åħ±è¯Ĩ
    0.10
    æĿ¥åĪ°äºĨ
    0.10
    åĪ°è¾¾
    0.10
    Conclusion
    0.10
    åĪ°äºĨ
    0.09
    Activations Density 0.077%

    No Known Activations