© 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. 439
    Prev
    Next
    INDEX
    Explanations

    academic requirements or course prerequisites

    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
    çŀ¬éĹ´
    -0.31
    æ¿Ģ
    -0.28
     millions
    -0.28
     движ
    -0.27
     ÄijÃłn
    -0.26
    å®ŀæŶ
    -0.26
     ÑĢад
    -0.26
    çŀ¬
    -0.25
     incredibly
    -0.25
    çĶ¨æīĭ
    -0.25
    POSITIVE LOGITS
    ä¸įå°ijäºİ
    0.43
    èĩ³å°ij
    0.40
     mandatory
    0.39
     compulsory
    0.39
    ä¸ĢéŨ
    0.37
     requirement
    0.37
     обÑıзаÑĤелÑĮ
    0.37
    ä¸įä½İäºİ
    0.36
     âī¥
    0.35
    è§Ħå®ļçļĦ
    0.34
    Activations Density 0.024%

    No Known Activations