© 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. 2006
    Prev
    Next
    INDEX
    Explanations

    for use with/in/on

    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
    太å¤ļ
    -0.27
    åı¯ä»¥è¯´
    -0.24
     enough
    -0.24
     Äijá»ģ
    -0.24
    éĤ£ä¹Ī容æĺĵ
    -0.23
    åıįèĢĮ
    -0.23
     idea
    -0.23
    ä¹Łä¸įåı¯èĥ½
    -0.23
    è¿ĻçĤ¹
    -0.22
    èĬ±å¼Ģ
    -0.22
    POSITIVE LOGITS
     purposes
    0.27
    å½ĵæĹ¥
    0.27
    à¸ļà¸Ļ
    0.26
     ASAP
    0.24
    äºİä¸Ģä½ĵ
    0.24
    äºİ
    0.23
     outdoors
    0.23
     within
    0.23
    alon
    0.23
    åīįåı°
    0.23
    Activations Density 0.060%

    No Known Activations