© 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. 34311
    Prev
    Next
    INDEX
    Explanations

    India and Indian culture

    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
    ãĥ¬ãĤ¹
    -0.10
    imas
    -0.10
     Pep
    -0.09
    amac
    -0.09
     Corpus
    -0.08
     Xin
    -0.08
    è±ģ
    -0.08
    .fb
    -0.08
    ẳ
    -0.08
     ÑĢеалÑĮно
    -0.08
    POSITIVE LOGITS
    åį°åº¦
    0.22
    Indian
    0.15
     India
    0.15
    India
    0.15
     Indian
    0.15
    åIJł
    0.14
     Indians
    0.14
     india
    0.13
     indian
    0.13
    ãĤ¤ãĥ³ãĥī
    0.12
    Activations Density 0.260%

    No Known Activations