© 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. 49639
    Prev
    Next
    INDEX
    Explanations

    Indian names and surnames

    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
    éĽ¨æ°´
    -0.10
    éĻį温
    -0.08
    ograms
    -0.08
    åIJĦçľģ
    -0.08
    çĵ¶é¢Ī
    -0.08
    matic
    -0.08
    rens
    -0.08
    éĩijåŃĹå¡Ķ
    -0.08
    åĦĺ
    -0.08
    bers
    -0.08
    POSITIVE LOGITS
    åį°åº¦
    0.21
     Indian
    0.15
    India
    0.15
    Indian
    0.14
     India
    0.14
    ãĤ¤ãĥ³ãĥī
    0.14
     india
    0.13
     Ấn
    0.13
     Gupta
    0.12
     Indians
    0.12
    Activations Density 0.260%

    No Known Activations