© 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. 60862
    Prev
    Next
    INDEX
    Explanations

    pronouns and names

    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æĪij
    -0.12
    对æĪij们
    -0.12
    让æĪij们
    -0.12
    æĪijåĴĮ
    -0.12
    对äºİæĪij们
    -0.12
    对æĪij说
    -0.11
    æĪijä¸Ģ缴
    -0.11
    æĪij们å¿ħé¡»
    -0.11
    æĪijéĥ½
    -0.11
    æĪij以为
    -0.11
    POSITIVE LOGITS
    è§īå¾Ĺèĩªå·±
    0.12
     himself
    0.11
    æĦŁåĪ°
    0.11
    æĦŁåıĹåĪ°äºĨ
    0.11
    æĥ³åĪ°
    0.10
    èĩªå·±çļĦ
    0.10
    feel
    0.10
    èĦijæµ·ä¸Ń
    0.10
     feel
    0.10
    æĦŁè§īèĩªå·±
    0.10
    Activations Density 0.080%

    No Known Activations