© 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. 21265
    Prev
    Next
    INDEX
    Explanations

    year-end

    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
    å°¼äºļ
    -0.12
    su
    -0.10
    enso
    -0.10
    ฯ
    -0.10
    çľ¼æ³ª
    -0.09
     handful
    -0.09
    å¿ĥæĦ¿
    -0.09
    åĨį说
    -0.09
    年级
    -0.09
    ðŁı»
    -0.09
    POSITIVE LOGITS
    lies
    0.11
    OfBirth
    0.10
    -old
    0.10
    rière
    0.10
    客æĪ·æıIJä¾Ľ
    0.09
    ä¼Ĭå§ĭ
    0.09
    èĢ½
    0.09
    ality
    0.09
    份
    0.09
    itative
    0.09
    Activations Density 0.055%

    No Known Activations