© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10183
    Prev
    Next
    INDEX
    Explanations

    social media platforms

    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
    2
    -0.08
    *
    -0.08
    1
    -0.08
    åľ¨ä¸Ģ个
    -0.07
     Hor
    -0.07
    çļĦåŃĺåľ¨
    -0.07
    anga
    -0.07
    4
    -0.07
    anger
    -0.07
    łģ
    -0.07
    POSITIVE LOGITS
    èĤĭ
    0.11
    ë´ī
    0.11
     Ath
    0.10
    赶
    0.10
     foss
    0.10
    ãģĬå¾Ĺ
    0.10
    好åIJĹ
    0.09
     Yayın
    0.09
    æŸ
    0.09
    RIX
    0.09
    Activations Density 0.006%

    No Known Activations