© 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. 1906
    Prev
    Next
    INDEX
    Explanations

    professional quality and results

    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
    亵
    -0.29
     obsc
    -0.27
    çĪ¹
    -0.25
    Advertisements
    -0.24
    æī¯
    -0.23
    ä¸Ģæŀļ
    -0.23
    æīĴ
    -0.23
     variants
    -0.23
    åį±å®³
    -0.23
     squ
    -0.23
    POSITIVE LOGITS
    顺åĪ©å®ĮæĪIJ
    0.34
    æĦŁè°¢
    0.32
    åľ¨æĪijçļĦ
    0.30
    æĦŁæ¿Ģ
    0.29
    满æĦı度
    0.29
    ä¼łçľŁ
    0.28
    æĦīå¿«
    0.28
    ãģĬãģĭãģĴ
    0.27
     professionalism
    0.27
    满æĦı
    0.27
    Activations Density 0.070%

    No Known Activations