© 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. 956
    Prev
    Next
    INDEX
    Explanations

    won consecutive titles

    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
    轻微
    -0.37
     minor
    -0.32
     locally
    -0.29
     prelim
    -0.28
    临æŶ
    -0.28
    éĻĦè¿ij
    -0.26
    ä¸Ģå°ı
    -0.26
     recycled
    -0.26
    minor
    -0.26
     temporary
    -0.25
    POSITIVE LOGITS
     unparalleled
    0.39
    顶å°ĸ
    0.38
    å·ħå³°
    0.38
    ä¸ĸçķĮä¸Ģæµģ
    0.35
    å·¨æĺŁ
    0.35
    å®Įç¾İ
    0.35
     superstar
    0.35
    åįĵè¶Ĭ
    0.34
    æĹłæķ°æ¬¡
    0.34
    æĹłæķĮ
    0.33
    Activations Density 0.083%

    No Known Activations