© 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. 50472
    Prev
    Next
    INDEX
    Explanations

    African places and 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
    uly
    -0.10
    æĩĭ
    -0.10
    æģ¯
    -0.09
    认
    -0.09
    æ§Ľ
    -0.09
    çĪ¸
    -0.09
    箬
    -0.09
     íļ
    -0.08
    èĭ¹æŀľ
    -0.08
    draw
    -0.08
    POSITIVE LOGITS
    éĿŀæ´²
    0.16
     African
    0.16
     Nigerian
    0.13
     Harlem
    0.12
     Nigeria
    0.12
     african
    0.12
    frican
    0.12
     Trinidad
    0.11
     Ghana
    0.11
    ðŁı¾
    0.11
    Activations Density 0.339%

    No Known Activations