© 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. 2023
    Prev
    Next
    INDEX
    Explanations

    pronouns and their context

    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
    è´µ
    -0.10
    对ä»ĸ
    -0.10
    è²´
    -0.09
    对æĪij
    -0.09
    åIJĪä½ľåħ³ç³»
    -0.09
    åµĺ
    -0.09
    atty
    -0.09
    åĬĽè¿ĺæĺ¯
    -0.09
    æĺ¯ä»ĸ
    -0.09
    ä¸Ĭåīį
    -0.09
    POSITIVE LOGITS
     Burr
    0.09
     Ñģамого
    0.09
    opus
    0.08
    èĢĮæĿ¥
    0.08
    trinsic
    0.08
    å±ķå¼Ģ
    0.08
    anan
    0.08
    åģļæ³ķ
    0.08
    drawing
    0.08
    rams
    0.08
    Activations Density 0.051%

    No Known Activations