© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1505
    Prev
    Next
    INDEX
    Explanations

    bring life to

    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
     taxes
    -0.26
    ä¸įåħį
    -0.25
    éĦĻ
    -0.24
    orrent
    -0.23
     deviation
    -0.23
     disposing
    -0.23
    æįİ
    -0.22
    Conclusion
    -0.22
    anford
    -0.22
    peration
    -0.22
    POSITIVE LOGITS
    é²ľæ´»
    0.35
    æ´»åĬĽ
    0.34
     flesh
    0.32
    çĶŁåĬ¨
    0.32
    çĶŁåij½åĬĽ
    0.32
    çģµåĬ¨
    0.31
    alive
    0.29
    çģµæ°Ķ
    0.28
     imagination
    0.28
    羣å®ŀ
    0.28
    Activations Density 0.025%

    No Known Activations