© 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. 2113
    Prev
    Next
    INDEX
    Explanations

    time followed by p.m

    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
    æľ¬æ¬¡
    -0.24
    outers
    -0.23
    ilter
    -0.23
    SupportedContent
    -0.22
    qualities
    -0.22
    -invalid
    -0.22
    åģ¥åº·çļĦ
    -0.21
    idge
    -0.21
    ä¸Ńç§ij
    -0.21
    帮å¿Ļ
    -0.21
    POSITIVE LOGITS
     noon
    0.25
    å¼ĢéŨ
    0.25
    ä¸ĩåįĥ
    0.24
    çĤ¹åįĬ
    0.24
    欢åij¼
    0.23
    onth
    0.22
     networking
    0.22
    æ¯Ļ
    0.22
     sweeping
    0.22
    ODO
    0.22
    Activations Density 0.021%

    No Known Activations