© 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. 52488
    Prev
    Next
    INDEX
    Explanations

    Linux system directories

    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
    sto
    -0.10
    æīĢåľ¨
    -0.09
    å³°
    -0.08
    èĩªèº«çļĦ
    -0.08
    交
    -0.08
    åij½ä¸Ń
    -0.08
    vant
    -0.08
    .allowed
    -0.08
    æľ¬èº«çļĦ
    -0.08
    eva
    -0.08
    POSITIVE LOGITS
    åºij
    0.09
    onz
    0.08
    åįļè§Ī
    0.08
    æĺİç¡®æıIJåĩº
    0.08
    Uid
    0.08
    ä½łä¼ļåıijçİ°
    0.08
    èįŁ
    0.08
    俾
    0.08
    æŃ¤æ¬¡æ´»åĬ¨
    0.08
    åŃ½
    0.08
    Activations Density 0.382%

    No Known Activations