© 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. 19514
    Prev
    Next
    INDEX
    Explanations

    Surface, Azure, Pixel

    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
    nin
    -0.09
    è´·
    -0.09
    èĵij
    -0.08
    nya
    -0.08
    req
    -0.08
    wg
    -0.08
    èħ¹
    -0.08
    sg
    -0.08
     tempered
    -0.08
    emet
    -0.08
    POSITIVE LOGITS
    æŁıæŀĹ
    0.10
    æĶ¹éĢł
    0.09
    棹
    0.09
    ropp
    0.09
    沦
    0.09
    -Cs
    0.09
     pie
    0.09
    gravity
    0.09
    滹
    0.08
    bios
    0.08
    Activations Density 0.017%

    No Known Activations