© 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. 1665
    Prev
    Next
    INDEX
    Explanations

    oftenother

    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
    дÑĥм
    -0.28
    伪
    -0.25
    æī°
    -0.24
    æł¼
    -0.23
    æł¡
    -0.23
     fours
    -0.22
    tower
    -0.22
     cub
    -0.21
    æŃ£
    -0.21
    fq
    -0.21
    POSITIVE LOGITS
    è¿Ļç±»
    0.32
    å¤ļåįĬ
    0.31
     Often
    0.30
    æĪĸå¤ļ
    0.30
    ä¸ĢäºĽ
    0.29
    æĪĸèĢħæĺ¯
    0.29
    Often
    0.29
    ä¸Ģç±»
    0.29
    often
    0.28
    æĪĸæĺ¯
    0.28
    Activations Density 0.434%

    No Known Activations