© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19622
    Prev
    Next
    INDEX
    Explanations

    differential effect

    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
    åĿļå®Ī
    -0.10
    èī¯å¿ĥ
    -0.09
    转移åĪ°
    -0.09
    ityEngine
    -0.09
    转移
    -0.09
    åģļå®Į
    -0.09
    æĬĬè¿ĻäºĽ
    -0.09
    ä¾ij
    -0.09
    oya
    -0.09
    ä¼ı
    -0.08
    POSITIVE LOGITS
    åĸ·
    0.10
    ä¸įéĢļ
    0.10
    å°ļ
    0.10
     Jet
    0.09
    ement
    0.09
    æ·ĭ
    0.09
    æ°´æµģ
    0.09
    ements
    0.09
    jet
    0.09
    æĭ§
    0.09
    Activations Density 0.091%

    No Known Activations