© 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. 39601
    Prev
    Next
    INDEX
    Explanations

    examine

    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
    ages
    -0.10
    chaft
    -0.10
    à¹ģà¸Ħ
    -0.10
    oks
    -0.10
    екÑģ
    -0.09
    age
    -0.09
    gi
    -0.09
    itionally
    -0.09
    fully
    -0.09
    à¹Ĥà¸Ļ
    -0.09
    POSITIVE LOGITS
    auc
    0.10
    åĬĽäºī
    0.10
    äºĨä¸įå°ij
    0.10
    ining
    0.09
    æĨ
    0.09
     closely
    0.09
    äºĨä¸Ģä¸ĭ
    0.09
    äºĨæĪijçļĦ
    0.08
    ÑģÑı
    0.08
    èĵ¬åĭĥ
    0.08
    Activations Density 0.041%

    No Known Activations