© 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. 2391
    Prev
    Next
    INDEX
    Explanations

    Oscar Wilde or mockingbird

    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
    æĪ¿äº§
    -0.09
    æĦıè§ģ
    -0.09
    SKI
    -0.09
    é£ĵ
    -0.09
    нÑĮ
    -0.09
    gang
    -0.09
    æŃ»äºĨ
    -0.09
    ç²¾åĬĽ
    -0.09
    åıĤçħ§
    -0.09
    ŀ
    -0.08
    POSITIVE LOGITS
     Moss
    0.09
    åīįåı°
    0.09
    æĥħ人
    0.09
    åĢĮ
    0.08
    wil
    0.08
     donor
    0.08
    ENUM
    0.08
    /owl
    0.08
    æĥ©æĪĴ
    0.08
    .languages
    0.08
    Activations Density 0.148%

    No Known Activations