© 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. 1531
    Prev
    Next
    INDEX
    Explanations

    my, our, your

    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
    åѦçĶŁçļĦ
    -0.12
    å®ŀä¹ł
    -0.09
    å®ļä½į
    -0.09
    alie
    -0.09
    æıĸ
    -0.08
    ãĤŃ
    -0.08
    人çļĦ
    -0.08
    家ä½ı
    -0.08
    åĪļ
    -0.08
    ILA
    -0.08
    POSITIVE LOGITS
    aug
    0.10
    çļĦèĦļæŃ¥
    0.09
    elm
    0.09
    ÑĢажа
    0.09
    .sendFile
    0.08
    è§Ĵ
    0.08
    åıĮèĦļ
    0.08
    缤纷
    0.08
    åĢ©
    0.08
    è¦ģä¸įçĦ¶
    0.08
    Activations Density 0.207%

    No Known Activations