© 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. 38890
    Prev
    Next
    INDEX
    Explanations

    medical documentation and evaluations

    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
    ICES
    -0.10
     Danger
    -0.10
     Achilles
    -0.10
    danger
    -0.09
    essages
    -0.09
    ucs
    -0.09
    CHA
    -0.09
    污æŁĵ
    -0.09
    ION
    -0.09
     Alo
    -0.09
    POSITIVE LOGITS
    çĬ¶åĨµ
    0.09
    ä¹ĭ举
    0.08
    .sparse
    0.08
    wav
    0.08
    -grade
    0.08
    ised
    0.08
     fins
    0.08
     Jag
    0.08
    庸
    0.08
    å®
    0.08
    Activations Density 0.021%

    No Known Activations