© 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. 62464
    Prev
    Next
    INDEX
    Explanations

    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
    ssel
    -0.10
    ç»ĦåĽ¢
    -0.09
    羣çĪ±
    -0.09
    羣å¿ĥ
    -0.09
    .tm
    -0.09
    ì§ķ
    -0.09
    combe
    -0.08
    ching
    -0.08
    èµŃ
    -0.08
    -sizing
    -0.08
    POSITIVE LOGITS
    Culture
    0.12
     Culture
    0.12
     culture
    0.12
    æĸĩåĮĸçļĦ
    0.12
    éĢĤåºĶ
    0.11
    æĸĩåĮĸ
    0.11
    culture
    0.11
    åİļåİļ
    0.10
    åįģåĪĨéĩįè¦ģ
    0.10
     кÑĥлÑĮÑĤÑĥ
    0.09
    Activations Density 0.060%

    No Known Activations