© 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. 6563
    Prev
    Next
    INDEX
    Explanations

    poverty and its consequences

    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
    çģĮ
    -0.09
    æ½¢
    -0.09
    æķ¢
    -0.09
    åħĨ
    -0.08
    åĩŃä»Ģä¹Ī
    -0.08
     обÑĢазом
    -0.08
    æŃ»äºĨ
    -0.08
    ç´¢èµĶ
    -0.08
    ÑĢÑĥг
    -0.08
     Restr
    -0.08
    POSITIVE LOGITS
    è´«åĽ°
    0.21
    è´«ç©·
    0.19
     poverty
    0.18
    貧
    0.16
     Poverty
    0.16
    ç©·
    0.13
    è´«
    0.13
    窮
    0.13
    æī¶è´«
    0.13
    è´«åĽ°äººåı£
    0.13
    Activations Density 0.042%

    No Known Activations