© 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. 53086
    Prev
    Next
    INDEX
    Explanations

    website domains

    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
    inous
    -0.09
    æīĭä¸ŃçļĦ
    -0.08
    *
    -0.08
    ist
    -0.08
     Toolkit
    -0.08
    enne
    -0.08
    instanc
    -0.08
    aled
    -0.08
    lish
    -0.07
    ****
    -0.07
    POSITIVE LOGITS
    lify
    0.10
    æĢİä¹Īæł·
    0.10
    被æī§è¡Į
    0.10
    éĻħ
    0.10
    網ç«Ļ
    0.10
    è¿Ļä¸ªåľ°åĽ¾
    0.10
    NewProp
    0.10
    笼罩
    0.09
    åIJĮåŁİ
    0.09
    é¦ĸè½®
    0.09
    Activations Density 0.120%

    No Known Activations