© 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. 1882
    Prev
    Next
    INDEX
    Explanations

    specializing in specific topics

    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
    æļ¹
    -0.27
    .mvp
    -0.25
     eyeb
    -0.25
    è¿ĺæĺ¯è¦ģ
    -0.25
    åĬłå·¥åİĤ
    -0.24
    车éĺŁ
    -0.24
    èĢĥèĻijåĪ°
    -0.23
     verb
    -0.23
     massages
    -0.23
    structors
    -0.23
    POSITIVE LOGITS
    é¢ĨåŁŁ
    0.29
     specializing
    0.28
     specializes
    0.27
    çŃīé¢ĨåŁŁ
    0.26
     agricultural
    0.25
     regional
    0.25
     terrorism
    0.24
    çªģåıijäºĭ件
    0.24
     specialty
    0.24
    é¢ĨåŁŁçļĦ
    0.24
    Activations Density 0.043%

    No Known Activations