© 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. 737
    Prev
    Next
    INDEX
    Explanations

    .spec, .txt, .start, Local

    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
     кнопк
    -0.25
    ÙħصÙĦØŃØ©
    -0.25
    Ø£Ùĩد
    -0.25
    æĭ¤
    -0.23
     ìĬ¤ìĬ¤
    -0.23
     конкÑĢ
    -0.23
     MERCHANTABILITY
    -0.22
    è·IJ
    -0.22
     моÑīн
    -0.22
    榰
    -0.22
    POSITIVE LOGITS
    	Id
    0.24
    	NULL
    0.21
    已被
    0.21
    	ST
    0.21
    	pc
    0.20
    	mesh
    0.20
    	dx
    0.20
    	sh
    0.19
    	Int
    0.19
    	View
    0.19
    Activations Density 4.059%

    No Known Activations