© 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. 53024
    Prev
    Next
    INDEX
    Explanations

    immigrants get benefits

    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
    ãģĹãģĭãģªãģĦ
    -0.10
    æĢµ
    -0.10
    éĻIJæŶ
    -0.10
     поÑĤеÑĢÑı
    -0.10
    åĬ¡å®ŀ
    -0.09
    æįIJ
    -0.09
     зÑĢ
    -0.09
    é¹ĥ
    -0.09
    è§ģè¯ģ
    -0.09
    羣æŃ£çļĦ
    -0.09
    POSITIVE LOGITS
    çī¹æĿĥ
    0.13
    éĢįéģ¥
    0.12
    _PAD
    0.11
    å¾ħéģĩ
    0.11
    åħįè´£
    0.10
    侥幸
    0.10
    宽æĿ¾
    0.10
    éĥ¨éķ¿
    0.10
    便åĪ©
    0.09
    _pad
    0.09
    Activations Density 0.128%

    No Known Activations