© 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. 1265
    Prev
    Next
    INDEX
    Explanations

    Q1, Q2, Q3, Q4

    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
    standing
    -0.25
    足
    -0.24
    æĿIJè´¨
    -0.23
    æķ´é½IJ
    -0.23
     bag
    -0.23
    /feed
    -0.22
     bottle
    -0.22
     stack
    -0.21
     instantaneous
    -0.21
     Ñį
    -0.21
    POSITIVE LOGITS
    è´¢æĬ¥
    0.35
    第ä¸īåŃ£åº¦
    0.34
    æľĪ份
    0.32
     season
    0.31
    åŃ£åº¦
    0.31
    æŶèĬĤ
    0.30
    ä¸ĬåįĬå¹´
    0.30
    åŃ£
    0.30
     seasons
    0.30
     months
    0.30
    Activations Density 0.013%

    No Known Activations