© 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. 53926
    Prev
    Next
    INDEX
    Explanations

    due to

    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
    ä¸įä¸ĭ
    -0.12
    ç´¯äºĨ
    -0.09
    д
    -0.09
    ÑĤеÑĢ
    -0.09
    oret
    -0.09
    rame
    -0.09
    TÄ°
    -0.09
    دÙĤ
    -0.09
    æĥ³çĿĢ
    -0.09
    º
    -0.09
    POSITIVE LOGITS
    ä»Ģä¹ĪåİŁåĽł
    0.13
     diligence
    0.10
    ired
    0.10
    çĶŁäº§æĢ»åĢ¼
    0.10
    å¿Ŀ
    0.09
    itarian
    0.09
    ç§įç§į
    0.09
    sville
    0.09
    -paying
    0.08
    leigh
    0.08
    Activations Density 0.028%

    No Known Activations