© 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. 2879
    Prev
    Next
    INDEX
    Explanations

    Japanese patent application

    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
    infer
    -0.27
    æģ¢å¤į
    -0.26
    æģ¢
    -0.24
     infer
    -0.23
     reconstruct
    -0.22
    åıªè§ģ
    -0.22
    rous
    -0.21
    ç²¾æ¹Ľ
    -0.21
    项
    -0.21
     forth
    -0.21
    POSITIVE LOGITS
    _override
    0.22
    ç½®
    0.22
    æħij
    0.22
    åħ¬æĬ¥
    0.21
    产ä¸ļåŁºåľ°
    0.21
    >{@
    0.21
    æµ®åĬ¨
    0.21
     nobody
    0.21
    åѤç«ĭ
    0.21
    Nobody
    0.20
    Activations Density 0.004%

    No Known Activations