© 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. 32061
    Prev
    Next
    INDEX
    Explanations

    confined to areas or space

    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
    åĮħ袱
    -0.10
    éĿ¢çĽ®
    -0.10
    fully
    -0.09
    çĺ¾
    -0.09
    ewn
    -0.09
    oric
    -0.09
    ami
    -0.09
    å¾Īå¤ļäºĭæĥħ
    -0.09
    MLE
    -0.09
    é¬ĵ
    -0.09
    POSITIVE LOGITS
    MENT
    0.11
    ä¸įä½ı
    0.11
    ä½ıäºĨ
    0.10
    å·²ä¹ħçļĦ
    0.10
    ment
    0.09
    Äĩ
    0.09
    erval
    0.09
    edly
    0.08
    å·´å·´
    0.08
    ining
    0.08
    Activations Density 0.019%

    No Known Activations