© 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. 1874
    Prev
    Next
    INDEX
    Explanations

    future developments or eventual outcomes

    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
    è¿ĺæľīå¾Īå¤ļ
    -0.24
     compliments
    -0.24
    æµģæ·Į
    -0.23
    èĬ±æľµ
    -0.23
    FH
    -0.22
    MAC
    -0.22
     COMPUTER
    -0.21
    人æĢ§
    -0.21
    å¾Ī大
    -0.21
    就读
    -0.21
    POSITIVE LOGITS
     later
    0.28
     eventual
    0.26
    åįıåķĨ
    0.25
     später
    0.24
    éļıçĿĢæŶéĹ´
    0.24
    éĢIJæŃ¥
    0.23
     eventually
    0.23
     dần
    0.23
    è¿ĩ渡
    0.23
    éĽı
    0.23
    Activations Density 0.094%

    No Known Activations