© 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. 61604
    Prev
    Next
    INDEX
    Explanations

    locations like Barracks, Resort, Capitol, Museum

    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
    èł¢
    -0.09
    è¿IJåĬ¨ä¼ļ
    -0.09
    ä¸Ģå¹´ä¸Ģ度
    -0.08
    ä¸ĢåĪĢ
    -0.08
     wr
    -0.08
    .TH
    -0.08
    umbling
    -0.07
    bury
    -0.07
    lac
    -0.07
    æ¯ķä¸ļ
    -0.07
    POSITIVE LOGITS
    å¤ļåĬŁèĥ½
    0.11
    çĮ·
    0.10
    çĶŃ
    0.10
    ç²īèī²
    0.10
    çłĶåıijä¸Ńå¿ĥ
    0.10
    宽æķŀ
    0.10
    è®®äºĭ
    0.09
    æĸ°ä¸ī
    0.09
    产ä¸ļåĽŃåĮº
    0.09
    容纳
    0.09
    Activations Density 0.153%

    No Known Activations