© 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. 4386
    Prev
    Next
    INDEX
    Explanations

    possessive nouns

    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
    æĪij们è¦ģ
    -0.10
    ologically
    -0.09
    /documentation
    -0.09
    被认为æĺ¯
    -0.08
    .Exists
    -0.08
    åĴĮæĶ¯æĮģ
    -0.08
    ä½łæĥ³
    -0.08
    ä½łä»¬
    -0.08
    _arguments
    -0.08
    ity
    -0.08
    POSITIVE LOGITS
    's
    0.23
    ìĿĺ
    0.23
    ’s
    0.23
    çļĦ大
    0.22
    çļĦå¿ĥ
    0.21
    çļĦå°ı
    0.21
    çļĦ
    0.20
    çļĦæľįåĬ¡
    0.20
    çļĦæĸ°
    0.19
    çļĦå®īåħ¨
    0.19
    Activations Density 0.334%

    No Known Activations