© 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. 21552
    Prev
    Next
    INDEX
    Explanations

    experience

    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
    çľ¼çļ®
    -0.10
    çļĦåij½è¿IJ
    -0.10
    dorf
    -0.09
    isti
    -0.09
    åij½è¿IJ
    -0.09
    rss
    -0.09
    秣
    -0.09
    omat
    -0.08
    afil
    -0.08
    è¦ģéĹ»
    -0.08
    POSITIVE LOGITS
    æķĻè®Ń
    0.10
    è¿Ļæĸ¹éĿ¢
    0.10
    atus
    0.09
     ÑĢабоÑĤÑĭ
    0.09
    裾
    0.09
    å°¾
    0.09
     tá»ĩ
    0.09
    angan
    0.09
    æī¿åĬŀ
    0.09
    érc
    0.08
    Activations Density 0.031%

    No Known Activations