© 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. 26556
    Prev
    Next
    INDEX
    Explanations

    Among the

    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
    aqu
    -0.09
    æ·ij
    -0.09
    Grant
    -0.09
     пÑĢоб
    -0.09
    chas
    -0.09
    .bd
    -0.09
    æĮĩæĮ¥
    -0.09
    éĤ³
    -0.08
     Aurora
    -0.08
    åĿ¦
    -0.08
    POSITIVE LOGITS
    ä¼Ĺå¤ļ
    0.11
    çľ¾
    0.09
    纷
    0.09
    ered
    0.09
    åħ¶ä»ĸçļĦ
    0.09
    åħ¶å®ĥ
    0.09
    å¤ļ项
    0.09
    æķĻç¨ĭ
    0.08
    ç¹ģ
    0.08
    åħ¶ä»ĸ
    0.08
    Activations Density 0.019%

    No Known Activations