© 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. 2026
    Prev
    Next
    INDEX
    Explanations

    a question mark or period

    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
     narrative
    -0.28
     resource
    -0.28
     social
    -0.27
     enduring
    -0.27
     Resource
    -0.27
     societal
    -0.27
     invited
    -0.26
     socio
    -0.26
     lived
    -0.26
     joined
    -0.26
    POSITIVE LOGITS
    è¦ģ注æĦı
    0.36
    æľĢ好ä¸įè¦ģ
    0.36
    误åĮº
    0.33
    éľĢè¦ģ注æĦı
    0.33
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.32
    ä¸ĢèĪ¬æĿ¥è¯´
    0.31
    è¦ģåıĬæŶ
    0.31
    å¦Ĥæŀľä½łæĥ³
    0.30
    åįĥä¸ĩä¸įè¦ģ
    0.29
    è¿ĻçĤ¹
    0.29
    Activations Density 0.123%

    No Known Activations