© 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. 5031
    Prev
    Next
    INDEX
    Explanations

    academic hospital

    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
    æĺ±
    -0.10
    对çŃĸ
    -0.09
    éĢĶ
    -0.09
    broadcast
    -0.09
    åģľçķĻ
    -0.09
     Hazard
    -0.08
    åĽ½æĥħ
    -0.08
    æĦŁåıĹ
    -0.08
    artz
    -0.08
    IEL
    -0.08
    POSITIVE LOGITS
    åĨħå¤ĸ
    0.10
    åİŁçIJĨ
    0.09
    æķĻ
    0.09
    åĨľåľº
    0.09
    allery
    0.08
     lou
    0.08
    æķĻãģĪ
    0.08
    红åĨĽ
    0.08
    彩票
    0.08
     Kern
    0.08
    Activations Density 0.204%

    No Known Activations