© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 292
    Prev
    Next
    INDEX
    Explanations

    university or college attended

    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
     viewers
    -0.28
    _hpp
    -0.26
     yourselves
    -0.25
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.25
     viewer
    -0.24
     cảnh
    -0.24
    èģĬèģĬ
    -0.23
    çŃīéĹ®é¢ĺ
    -0.23
    æľįåĬ¡æľºæŀĦ
    -0.23
    pone
    -0.22
    POSITIVE LOGITS
     afforded
    0.31
     followed
    0.28
     granted
    0.28
     preceded
    0.27
    åīįç½®
    0.26
    åIJĪæł¼
    0.26
     specializing
    0.25
    è±ģ
    0.25
     Childhood
    0.25
     completed
    0.25
    Activations Density 0.119%

    No Known Activations