© 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. 2627
    Prev
    Next
    INDEX
    Explanations

    want to happen

    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
    å¾Īä¸įéĶĻ
    -0.26
     various
    -0.26
    æĥ³åĪ°äºĨ
    -0.25
    issa
    -0.25
     remarkably
    -0.25
    æĹ¥æŃ£å¼ı
    -0.24
    æľ¬æľŁ
    -0.24
    Various
    -0.24
    ways
    -0.23
     Various
    -0.23
    POSITIVE LOGITS
     anymore
    0.43
    æľīä»»ä½ķ
    0.42
     unnecessarily
    0.41
    ä¸įå¿ħè¦ģçļĦ
    0.40
    ä»»ä½ķå½¢å¼ı
    0.33
    è¿ĩå¤ļ
    0.33
     unnecessary
    0.32
    ä»»ä½ķ
    0.29
    è½»æĺĵ
    0.28
    太å¤ļ
    0.28
    Activations Density 0.087%

    No Known Activations