© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37133
    Prev
    Next
    INDEX
    Explanations

    finding myself

    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
    ICODE
    -0.09
    ساÙħ
    -0.08
    quil
    -0.08
    à¸ģารà¹ģสà¸Ķà¸ĩ
    -0.08
    åıĤ
    -0.08
    dì
    -0.08
    ouver
    -0.08
    ograms
    -0.08
    .custom
    -0.08
    .Restr
    -0.08
    POSITIVE LOGITS
    è¶ĬæĿ¥è¶Ĭ大
    0.11
    è¶ĬæĿ¥è¶Ĭ好
    0.10
    éĿŀ常å¤ļçļĦ
    0.10
    æļĹæļĹ
    0.10
    ä¸į该
    0.10
    佩æľį
    0.10
    潸
    0.10
    ä¸įèĪĴæľį
    0.09
    è¶ĬæĿ¥è¶Ĭ
    0.09
    èIJ¥åķĨ
    0.09
    Activations Density 0.021%

    No Known Activations