© 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. 53214
    Prev
    Next
    INDEX
    Explanations

    statistical analysis

    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
    eras
    -0.10
    adero
    -0.09
    ders
    -0.09
    éķľ
    -0.09
    RuntimeObject
    -0.09
    æĺİç¡®æıIJåĩº
    -0.09
    å¸
    -0.08
    èĦ©
    -0.08
    夺åĨł
    -0.08
    ç«Ļ
    -0.08
    POSITIVE LOGITS
    åĪĨæŀIJ
    0.27
     analysis
    0.23
     Analysis
    0.18
    analysis
    0.18
    Analysis
    0.17
     анализ
    0.16
     análisis
    0.15
    _analysis
    0.15
     análise
    0.15
     analyze
    0.14
    Activations Density 0.209%

    No Known Activations