© 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. 2828
    Prev
    Next
    INDEX
    Explanations

    not ... you won't

    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
     neither
    -0.27
    ä¸į论
    -0.24
    ä¸įåĪĨ
    -0.24
    ney
    -0.23
    eri
    -0.23
    ikh
    -0.23
     census
    -0.22
    ç¡®ä¿Ŀ
    -0.22
    并ä¸įæĺ¯
    -0.22
    cess
    -0.22
    POSITIVE LOGITS
    Ø£Ùĩد
    0.27
    Ø£ÙĪضاع
    0.24
    -done
    0.24
    è¿ĽæŃ¥
    0.23
     пÑĢоиÑģ
    0.23
    åģļè¿ĩ
    0.23
    å¤ĸçķĮ
    0.22
    Ø£ÙģÙĦ
    0.22
    inline
    0.22
    åıijæĮ¥ä½ľçĶ¨
    0.22
    Activations Density 0.019%

    No Known Activations