© 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. 721
    Prev
    Next
    INDEX
    Explanations

    priority sector, special class, enrollment

    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
    äºĨä¸Ģåľº
    -0.24
     fant
    -0.23
    ç»ıå¼Ģ
    -0.23
    ç«ĭæĸ¹
    -0.22
    迷失
    -0.22
    å¹»æĥ³
    -0.22
    çİ°è´§
    -0.22
    æĹłç¼ĺ
    -0.22
    梦
    -0.21
    çĭĤ欢
    -0.21
    POSITIVE LOGITS
    é¼ĵåĬ±
    0.55
    ä¼ĺåħĪ
    0.52
    çī¹æ®Ĭ
    0.52
    æī¶æĮģ
    0.51
    ä¼ĺæĥłæĶ¿çŃĸ
    0.50
     special
    0.46
    åĢ¾æĸľ
    0.46
     incentiv
    0.45
     priority
    0.44
    çī¹æ®ĬçļĦ
    0.43
    Activations Density 0.162%

    No Known Activations