© 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. 6817
    Prev
    Next
    INDEX
    Explanations

    nationalities and associated people

    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
    åıĭ们
    -0.10
    ä¸Ģå¤Ħ
    -0.10
    è¿Ļç§įæĥħåĨµ
    -0.10
    ä¸Ģç§į
    -0.09
    åı¦ä¸Ģè¾¹
    -0.09
    ä¸Ģç±»
    -0.09
    å¹´ä¸ĬåįĬå¹´
    -0.09
    äºĨä¸Ģéģį
    -0.08
    èĩªèº«çļĦ
    -0.08
    åı¦ä¸Ģ
    -0.08
    POSITIVE LOGITS
    zac
    0.09
    ERY
    0.08
     добÑĢо
    0.08
    弶
    0.08
    /non
    0.08
    calar
    0.08
    yat
    0.08
    æľĭåıĭ
    0.08
    experimental
    0.08
    polit
    0.08
    Activations Density 0.096%

    No Known Activations