© 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. 63317
    Prev
    Next
    INDEX
    Explanations

    engineering and engineers

    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
    ãģ£ãģįãĤĬ
    -0.10
    æºIJæºIJ
    -0.10
    ç§ijåѦåıijå±ķ
    -0.09
    ensions
    -0.09
    éħĭ
    -0.09
    讳
    -0.09
    zelf
    -0.09
    иж
    -0.09
    Ìģ
    -0.09
    主ä¹īæĢĿæĥ³
    -0.09
    POSITIVE LOGITS
    ered
    0.14
    師
    0.10
    angelo
    0.09
    erd
    0.09
    Ùħا
    0.09
    ÑĤÑĢ
    0.09
    stown
    0.09
    IAN
    0.09
    ur
    0.09
    erm
    0.09
    Activations Density 0.014%

    No Known Activations