© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48096
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by attributes

    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
    å·¡
    -0.09
     Hen
    -0.09
    丰
    -0.08
    quia
    -0.08
    æºIJ头
    -0.08
    çĺ¾
    -0.08
    atica
    -0.08
    quÃŃ
    -0.08
    วà¸Ļ
    -0.08
    arak
    -0.08
    POSITIVE LOGITS
    年纪
    0.16
    å¹´é¾Ħ
    0.13
     age
    0.12
    å¹´é¾Ħ段
    0.12
    -aged
    0.12
    æĿ¡ä»¶ä¸ĭ
    0.11
    ä½ĵéĩı
    0.11
    è¿ĻèĪ¬
    0.11
    éĤ£æł·çļĦ
    0.11
    size
    0.11
    Activations Density 0.055%

    No Known Activations