© 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. 643
    Prev
    Next
    INDEX
    Explanations

    good hot, good mash, good knee, good game

    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
     concerned
    -0.28
    详ç»ĨäºĨ解
    -0.26
    å¾Īå¼Ģå¿ĥ
    -0.26
    å¯ĨåĪĩåħ³æ³¨
    -0.25
    äºĨä»ĸçļĦ
    -0.25
    å®Ĺ
    -0.24
     considerations
    -0.23
    äºĨ大éĩıçļĦ
    -0.22
    stud
    -0.22
    æĭħå¿ĥ
    -0.21
    POSITIVE LOGITS
    auce
    0.29
    åįģæĿ¡
    0.24
    ycle
    0.24
    ysz
    0.23
    ä¸ĢåĽŀäºĭ
    0.23
    åį§
    0.23
    ви
    0.22
    EDIA
    0.22
    ddit
    0.22
     tamp
    0.21
    Activations Density 0.013%

    No Known Activations