© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 931
    Prev
    Next
    INDEX
    Explanations

    personal statements about "me"

    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
    让å®ĥ
    -0.10
    让
    -0.10
    åħ¶æīĢ
    -0.09
    åı¯ä»¥è®©
    -0.09
    让ä»ĸ们
    -0.09
    让大家
    -0.09
    让人们
    -0.09
    agraph
    -0.09
    obe
    -0.09
    icina
    -0.08
    POSITIVE LOGITS
    æĿ¥è¯´
    0.13
    æĿ¥è®²
    0.12
    /her
    0.12
    èĢĮè¨Ģ
    0.10
    cht
    0.10
    ä¹Łä¸įä¾ĭå¤ĸ
    0.09
    ä¾Ĩ說
    0.09
    /us
    0.09
    ansa
    0.09
    yan
    0.08
    Activations Density 0.025%

    No Known Activations