© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38163
    Prev
    Next
    INDEX
    Explanations

    adjectives after conjunctions

    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
    packed
    -0.10
    é¹Ĭ
    -0.10
    DED
    -0.10
    ÑĤив
    -0.09
    veis
    -0.09
    ibern
    -0.09
    æľīè¿Ļæł·çļĦ
    -0.09
    IGNED
    -0.09
    æİĸ
    -0.09
    eres
    -0.09
    POSITIVE LOGITS
    å¹´ä¹ĭ
    0.09
     halls
    0.08
    3
    0.08
    7
    0.08
    9
    0.08
     мало
    0.08
    8
    0.08
    çªĴ
    0.08
    åĩ¡æľ¬ç½ij
    0.08
    çĹķ
    0.08
    Activations Density 0.117%

    No Known Activations