© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2799
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns + nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     entirety
    -0.31
     entire
    -0.24
    çļĦåĨ³å¿ĥ
    -0.24
    ä¸Ģäºĭ
    -0.24
    outh
    -0.24
     same
    -0.23
     inability
    -0.23
     presumption
    -0.23
    è¿Ļ个è¯į
    -0.23
     socialism
    -0.23
    POSITIVE LOGITS
    åħ¶ä»ĸ
    0.25
    æĪIJåijĺ
    0.24
    顶级
    0.24
    代表æĢ§
    0.24
    åİĨ
    0.24
    常è§Ħ
    0.23
    åı¯ä¾Ľ
    0.23
    缸å½ĵ
    0.23
     acquaint
    0.23
    个æĢ§
    0.23
    Activations Density 0.033%

    No Known Activations