© 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. 63569
    Prev
    Next
    INDEX
    Explanations

    place names ending in shire or ampton

    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
    éĤĽ
    -0.10
    èļĢ
    -0.10
    éĵ¡
    -0.09
     Georgetown
    -0.09
    æĥ©
    -0.09
    ç½ļ
    -0.08
     Tin
    -0.08
    éĻķ
    -0.08
    getBytes
    -0.08
    æīĢåģļçļĦ
    -0.08
    POSITIVE LOGITS
    æĹºçĽĽ
    0.09
    _MAT
    0.09
    ickey
    0.09
    acci
    0.09
    赶ä¸Ĭ
    0.09
    forge
    0.08
    illage
    0.08
    çı°
    0.08
    ç¯ĩç«ł
    0.08
    æĪĹ
    0.08
    Activations Density 0.054%

    No Known Activations