© 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. 736
    Prev
    Next
    INDEX
    Explanations

    Category lists

    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
    车éĺŁ
    -0.26
     spins
    -0.24
     zen
    -0.22
    æľ¬èµĽåŃ£
    -0.22
     frais
    -0.21
    è¸ıåħ¥
    -0.21
    车éģĵ
    -0.21
    æİ¥åIJ¬
    -0.21
    å½±éĻ¢
    -0.21
    alis
    -0.21
    POSITIVE LOGITS
     Interest
    0.26
    ROC
    0.25
     Records
    0.25
     interest
    0.24
    gtest
    0.24
     Fam
    0.23
     relations
    0.23
     Relations
    0.23
    åľ¨ä»ĸçļĦ
    0.23
    topic
    0.23
    Activations Density 0.043%

    No Known Activations