© 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. 18362
    Prev
    Next
    INDEX
    Explanations

    Indian surnames and 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
    åIJĪä¸Ģ
    -0.10
    REEN
    -0.09
    æıIJ示
    -0.09
     vent
    -0.09
    éĢł
    -0.09
    累计
    -0.09
     Alic
    -0.09
    ittal
    -0.09
    acro
    -0.08
    ocz
    -0.08
    POSITIVE LOGITS
    çļĦæ¯į亲
    0.09
    çĥ¦èºģ
    0.09
    åį´è¢«
    0.09
     Kumar
    0.08
    çĮ¥
    0.08
    .svg
    0.08
    Ñĩик
    0.08
    èĩªæĿĢ
    0.08
    å¿ĥ头
    0.08
    å²£
    0.08
    Activations Density 0.051%

    No Known Activations