© 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. 52243
    Prev
    Next
    INDEX
    Explanations

    quotes and apostrophes

    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
    ÑĦин
    -0.09
    ãģĹãģ¾
    -0.09
    APTER
    -0.09
    bsp
    -0.09
    æīĵãģ¡
    -0.09
    Łèĥ½
    -0.09
    åħ¨æĹ¥åĪ¶
    -0.09
    èIJ¥
    -0.08
    ews
    -0.08
     Extr
    -0.08
    POSITIVE LOGITS
    åķ¼
    0.11
    uft
    0.09
    æ·¡åĮĸ
    0.09
    éĻĦ件
    0.09
    loud
    0.09
    ç¦Ħ
    0.09
    åĿļ
    0.09
    éģĹ
    0.08
    .Diagnostics
    0.08
    roman
    0.08
    Activations Density 0.114%

    No Known Activations