© 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. 10027
    Prev
    Next
    INDEX
    Explanations

    Indian surnames ending in 'ra' or 'inder'/'inda'

    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
    礴
    -0.09
    ity
    -0.09
    gua
    -0.09
     cant
    -0.09
    acre
    -0.09
    ãĥ¥
    -0.09
    ãĤŃãĥ£ãĥ³
    -0.09
    æ§Ľ
    -0.09
    å²·
    -0.09
    ç§ķ
    -0.09
    POSITIVE LOGITS
    妹åŃIJ
    0.12
    ustr
    0.11
    æľĪèĸª
    0.09
    èĥ¯
    0.09
    .norm
    0.09
    åħĭæľį
    0.08
    åıĪèĥ½
    0.08
     anth
    0.08
    ships
    0.08
    UNCH
    0.08
    Activations Density 0.017%

    No Known Activations