© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14589
    Prev
    Next
    INDEX
    Explanations

    possession and ownership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    bone
    -0.17
    yü
    -0.16
    è·ijéģĵ
    -0.16
    onaut
    -0.15
    bian
    -0.15
    ivec
    -0.15
    lü
    -0.14
    -runner
    -0.14
    YPE
    -0.14
    ioc
    -0.14
    POSITIVE LOGITS
    -fashioned
    0.20
    è¯Ŀè¯ŃæĿĥ
    0.20
    liest
    0.19
    liness
    0.19
    OrUpdate
    0.19
    å¨ĺ
    0.19
    /operators
    0.18
    è¿Ļä¸ĢåĪĩ
    0.18
    å¾Ĺèµ·
    0.17
    ies
    0.17
    Activations Density 0.037%

    No Known Activations