© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 950
    Prev
    Next
    INDEX
    Explanations

    ownership stakes

    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
    箨
    -0.29
    à¸Ľà¸£à¸°à¸Īำ
    -0.23
     anecd
    -0.23
     Pressure
    -0.23
    stown
    -0.22
    æļijåģĩ
    -0.22
    çªĺ
    -0.22
    ä¸įèī¯ä¿¡æģ¯
    -0.22
     Suggestions
    -0.22
    对çħ§
    -0.21
    POSITIVE LOGITS
     ownership
    0.37
    ownership
    0.32
    份é¢Ŀ
    0.31
     rights
    0.30
    çĻ¾åĪĨä¹ĭ
    0.30
    æĿĥçĽĬ
    0.28
    èĤ¡æĿĥ
    0.28
     owns
    0.28
    rights
    0.28
    æīĢæľīæĿĥ
    0.27
    Activations Density 0.011%

    No Known Activations