© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 662
    Prev
    Next
    INDEX
    Explanations

    retrospective review of records

    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
     hardly
    -0.24
     things
    -0.23
    è¿ĺæľīä»Ģä¹Ī
    -0.23
    èį·èĬ±
    -0.23
     famously
    -0.23
     barely
    -0.23
     always
    -0.23
    -heavy
    -0.22
    éļ³
    -0.22
     toughest
    -0.22
    POSITIVE LOGITS
    æŶéĹ´ä¸º
    0.29
    ä¸ĢåIJį
    0.28
    çĹħä¾ĭ
    0.27
    æĶ¶éĽĨ
    0.26
    ä¸ºæľŁ
    0.26
     purpos
    0.25
    åĪ¶å®ļäºĨ
    0.25
    semi
    0.25
    å°±è¯Ĭ
    0.24
     randomly
    0.24
    Activations Density 1.770%

    No Known Activations