© 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. 8750
    Prev
    Next
    INDEX
    Explanations

    determiners and demonstratives

    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
    ENTA
    -0.10
    彩
    -0.10
    åĩºæĿ¥
    -0.09
    inherits
    -0.09
    getic
    -0.09
    ETY
    -0.09
    .nz
    -0.09
    tif
    -0.09
    imits
    -0.09
    åĩºè¡Į
    -0.09
    POSITIVE LOGITS
    /off
    0.11
    /down
    0.10
    wards
    0.09
    fter
    0.09
    äºĨä¸ĢäºĽ
    0.08
    æ¿ĢåĬ¨
    0.08
    鸷
    0.08
    ç²¾é«ĵ
    0.08
     ord
    0.08
    éĽį
    0.08
    Activations Density 0.134%

    No Known Activations