© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7438
    Prev
    Next
    INDEX
    Explanations

    park as a location

    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
    ç°ª
    -0.10
    å¾Ģå¤ĸ
    -0.10
    combe
    -0.10
    å°¼æĸ¯
    -0.10
    ÏĤ
    -0.09
    æĪijçľĭ
    -0.09
    ÑģÑĮ
    -0.09
    çijķ
    -0.09
    åģļ人
    -0.09
    ÑĢод
    -0.09
    POSITIVE LOGITS
    inson
    0.12
    ษา
    0.10
    ings
    0.09
    side
    0.09
    人士
    0.09
    lights
    0.09
    house
    0.09
    maid
    0.09
    wide
    0.08
    inder
    0.08
    Activations Density 0.028%

    No Known Activations