© 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. 57141
    Prev
    Next
    INDEX
    Explanations

    rightly is seen or says

    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
    çĶ¸
    -0.10
    ä¹Łä¸įçŁ¥éģĵ
    -0.09
    .Dense
    -0.09
    åĿij
    -0.09
    ä½łæĢİä¹Ī
    -0.08
    /goto
    -0.08
    ByExample
    -0.08
    缴è¾ĸ
    -0.08
    å»īä»·
    -0.08
    bart
    -0.08
    POSITIVE LOGITS
    æŶæĬ¥
    0.09
    å¦ĤæѤ
    0.09
    é¢ĦæľŁ
    0.09
    æī°
    0.09
    åĽŀäºĭ
    0.09
    åĢĻ
    0.09
    娣
    0.09
    åIJĦ项
    0.09
    æĸĩåĮĸèĬĤ
    0.08
    è¿ĻèĪ¬
    0.08
    Activations Density 0.038%

    No Known Activations