© 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. 34207
    Prev
    Next
    INDEX
    Explanations

    Latin American and Caribbean countries

    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
    поÑĤ
    -0.09
    åĴ¸éĺ³
    -0.09
     po
    -0.09
     cann
    -0.08
    æ¼ķ
    -0.08
    anni
    -0.08
    æIJľ
    -0.08
     McCorm
    -0.08
    æ°Ķè¡Ģ
    -0.08
    _transition
    -0.07
    POSITIVE LOGITS
    糯
    0.10
    æݨ广åºĶçĶ¨
    0.10
    çĭ®
    0.10
    ç²ľ
    0.09
    çĥŃ带
    0.09
    åĶĩ
    0.09
    廪
    0.09
    èĩªçĦ¶ä¿ĿæĬ¤
    0.09
    èľĪ
    0.09
    éª
    0.09
    Activations Density 0.130%

    No Known Activations