© 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. 50454
    Prev
    Next
    INDEX
    Explanations

    cause and effect, mortality explanations

    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
    ç®ķ
    -0.12
    Vir
    -0.09
     vir
    -0.09
    .Dependency
    -0.09
     mach
    -0.08
     Vir
    -0.08
     coff
    -0.08
    çļĦ妻åŃIJ
    -0.08
     завиÑģим
    -0.07
     grounding
    -0.07
    POSITIVE LOGITS
    å®ĺ
    0.11
    è¿ĺä¸įæĺ¯
    0.10
    åįķ纯çļĦ
    0.10
    åįĩåѦ
    0.10
    缱
    0.10
    encv
    0.10
     chứ
    0.10
    èİŀ
    0.10
    ä»Ģä¹ĪåİŁåĽł
    0.10
    ç¾İæĸ¹
    0.09
    Activations Density 0.038%

    No Known Activations