© 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. 1938
    Prev
    Next
    INDEX
    Explanations

    When you

    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
    å½ĵæŶçļĦ
    -0.33
    å½ĵæŶ
    -0.32
    woke
    -0.29
    åıijçĶŁåľ¨
    -0.27
    æ²ī
    -0.27
    éĤ£æĺ¯
    -0.26
    æķħæĦı
    -0.26
     previous
    -0.26
     rel
    -0.25
     earlier
    -0.25
    POSITIVE LOGITS
    å®ĮæĪIJåIJİ
    0.28
    ä½łéľĢè¦ģ
    0.28
    åį³åı¯
    0.26
    æĤ¨åı¯ä»¥
    0.26
     setUp
    0.26
    setUp
    0.25
     chaque
    0.25
     SETUP
    0.25
    /releases
    0.24
    åı¯ä»¥å¸®åĬ©
    0.24
    Activations Density 0.065%

    No Known Activations