© 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. 3624
    Prev
    Next
    INDEX
    Explanations

    years, dates, and numbers

    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
    phans
    -0.12
    anguage
    -0.10
    swith
    -0.10
    woke
    -0.09
    acles
    -0.09
    /from
    -0.09
    lius
    -0.09
    åĬłæĭ¿
    -0.08
    udes
    -0.08
    tings
    -0.08
    POSITIVE LOGITS
    -Javadoc
    0.10
    ÑįÑĤомÑĥ
    0.09
     Shen
    0.09
    âĸ°
    0.09
    phalt
    0.09
    ear
    0.09
    re
    0.08
    ä¹Łæľīä¸ĢäºĽ
    0.08
    æĪijä¸Ģ缴
    0.08
    绿èī²éĢļéģĵ
    0.08
    Activations Density 0.263%

    No Known Activations