© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 2628
    Prev
    Next
    INDEX
    Explanations

    demographic groups and statistics

    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
    -interest
    -0.23
    istencia
    -0.23
     interests
    -0.23
     complementary
    -0.23
    åı¯ç͍
    -0.22
    ebra
    -0.22
    vern
    -0.22
    æĹ¨
    -0.22
    éľ²
    -0.22
    åı¯ä»¥éĢļè¿ĩ
    -0.22
    POSITIVE LOGITS
    尤为
    0.31
     Overall
    0.26
    Overall
    0.25
     percentages
    0.25
    Percentage
    0.24
    ahun
    0.23
    å°¤åħ¶æĺ¯
    0.23
     proportion
    0.23
     propor
    0.23
    percentage
    0.22
    Activations Density 0.141%

    No Known Activations