© 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. 53747
    Prev
    Next
    INDEX
    Explanations

    east asia and africa

    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
    çĿ¬
    -0.10
    erate
    -0.09
    æ©ĩ
    -0.09
    ï¸ı
    -0.08
    éĿ¢å¯¹éĿ¢
    -0.08
    ä¹ĭ乡
    -0.08
    ÑĪка
    -0.08
    hare
    -0.08
    è·µ
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    POSITIVE LOGITS
    ward
    0.12
    most
    0.12
    lake
    0.11
    ern
    0.11
    ablish
    0.11
     dÃłng
    0.11
    rix
    0.11
    minster
    0.10
    iveness
    0.10
    æĥħæĢĢ
    0.10
    Activations Density 0.063%

    No Known Activations