© 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. 557
    Prev
    Next
    INDEX
    Explanations

    specific scenarios

    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
    éĢĻ麼
    -0.32
    åĪ°è¿ĻéĩĮ
    -0.28
    éĤ£ä¹Īç®Ģåįķ
    -0.28
    è¿Ļæĺ¯æĪij
    -0.28
    è¿Ļä¹Īå¤ļ
    -0.27
    è¿Ļæł·æīįèĥ½
    -0.27
    è¿Ļä¹Ī大
    -0.27
    è¿ĻéĩĮæĺ¯
    -0.25
     dabei
    -0.25
    ãģĵãģĵãģ¾ãģ§
    -0.25
    POSITIVE LOGITS
    ä¸įä½Ĩ
    0.35
    å°±éľĢè¦ģ
    0.32
    è¦ģä¹Ī
    0.27
    ä¸įä»ħ
    0.26
    便åı¯
    0.24
    便
    0.24
    åį³ä½¿
    0.24
     either
    0.24
    æĪijçĽ¸ä¿¡
    0.24
    å°±ä¸įä¼ļ
    0.24
    Activations Density 0.101%

    No Known Activations