© 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. 2200
    Prev
    Next
    INDEX
    Explanations

    range from

    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
    çļĦåIJĮæŶ
    -0.27
    ä¹ĭä½Ļ
    -0.26
     meantime
    -0.25
    itude
    -0.24
     meanwhile
    -0.23
    åĢĴæĺ¯
    -0.23
    ãģ°ãģĭãĤĬ
    -0.23
    eness
    -0.22
    quals
    -0.22
    etas
    -0.21
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.30
     downright
    0.29
     пÑĢоÑģÑĤо
    0.28
     purely
    0.26
    ä¸įåIJĮç¨ĭ度
    0.26
     outright
    0.26
     mildly
    0.25
    轻微
    0.23
     highly
    0.23
     permanent
    0.23
    Activations Density 0.023%

    No Known Activations