© 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. 19732
    Prev
    Next
    INDEX
    Explanations

    code following file extensions

    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
    åħħ足çļĦ
    -0.09
    æĶ¹å»º
    -0.09
    iete
    -0.09
    perse
    -0.09
    ä»»ä½ķ人
    -0.08
    egin
    -0.08
    åħħåĪĨ
    -0.08
    ç¼Ķ
    -0.08
    åłª
    -0.08
    çł¥
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĽŀäºĭ
    0.10
    åĪ¤
    0.09
    缯
    0.09
    ÑĢ
    0.09
    åijĪçİ°åĩº
    0.09
    æ¹¾
    0.09
     Morgan
    0.09
     Donovan
    0.08
    buat
    0.08
    ano
    0.08
    Activations Density 0.011%

    No Known Activations