© 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. 22177
    Prev
    Next
    INDEX
    Explanations

    blog writings

    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
    å»ĵ
    -0.09
    addon
    -0.09
    ç¥Ŀ
    -0.08
    èģ
    -0.08
    sen
    -0.08
    åĵij
    -0.08
    æī
    -0.08
     sen
    -0.07
    è´º
    -0.07
    æį
    -0.07
    POSITIVE LOGITS
    妹åŃIJ
    0.11
    åıijå±ķè§ĦåĪĴ
    0.10
    chron
    0.10
    ysz
    0.10
    imits
    0.10
    éĩĮçļĦ
    0.10
    æľ¬ç«Ļ
    0.10
    éĢīåĿĢ
    0.10
    /Gate
    0.09
    主页
    0.09
    Activations Density 0.027%

    No Known Activations