© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21165
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    ода
    -0.10
    _PAGES
    -0.09
    çīĿ
    -0.09
    angen
    -0.09
    .books
    -0.08
    å»ºè®¾é¡¹çĽ®
    -0.08
    让çĶ¨æĪ·
    -0.08
     ÑĥÑģп
    -0.08
    ç»·
    -0.08
    çļ´
    -0.08
    POSITIVE LOGITS
     же
    0.11
    个人è§ĤçĤ¹
    0.09
     Bros
    0.09
    åħĦ
    0.08
    è´Łè´£
    0.08
    æIJŃæ¡£
    0.08
     Gill
    0.08
    导è´Ń
    0.08
    论
    0.07
    æĪĸèĢħåħ¶ä»ĸ
    0.07
    Activations Density 0.155%

    No Known Activations