© 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. 33089
    Prev
    Next
    INDEX
    Explanations

    country names

    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
    们
    -0.12
    iden
    -0.11
    ä¼ļéķ¿
    -0.10
    ä¸ŃåĽ½çī¹èī²
    -0.09
    acts
    -0.09
    ould
    -0.09
    ä¸ŃåĽ½äºº
    -0.09
    een
    -0.09
    们éĥ½
    -0.09
    åĮºç®¡å§Ķä¼ļ
    -0.09
    POSITIVE LOGITS
    佬
    0.14
    -Israel
    0.13
    -wide
    0.12
    ç±į
    0.12
    anness
    0.12
    -born
    0.11
    æľ¬åľŁ
    0.11
    -specific
    0.10
    riad
    0.10
    Ìģ
    0.10
    Activations Density 0.237%

    No Known Activations