© 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. 722
    Prev
    Next
    INDEX
    Explanations

    printer driver device connection

    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
    åij¨è½¬
    -0.27
    缴èIJ¥
    -0.25
     decks
    -0.23
    éĤªæģ¶
    -0.23
     vanilla
    -0.23
    å¿ĥæĻº
    -0.23
     arity
    -0.22
    Deck
    -0.22
     Deck
    -0.22
    èıĸ
    -0.22
    POSITIVE LOGITS
    åºĶåıĬæŶ
    0.25
     Cone
    0.25
     Prompt
    0.25
     Administrative
    0.24
    主管éĥ¨éŨ
    0.24
    laps
    0.23
    æĹłç¼Ŀ
    0.23
    è¿ħéĢŁ
    0.23
    åıĬæŶ
    0.23
     rolled
    0.22
    Activations Density 0.052%

    No Known Activations