© 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. 979
    Prev
    Next
    INDEX
    Explanations

    God, Lord, glory, testcase, function

    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
    åįģä¸Ģ
    -0.24
    ªĮ
    -0.24
    ully
    -0.23
     patri
    -0.22
    deaux
    -0.22
    weights
    -0.21
    éªĮè¯ģ
    -0.21
    è¡¡éĩı
    -0.21
     Snake
    -0.20
    çļĦæĦ¿æľĽ
    -0.20
    POSITIVE LOGITS
    çĥŁåĽ±
    0.24
     поÑĤеÑĢ
    0.23
    ä¸ĢçĤ¹
    0.23
    Äĥr
    0.23
     Dank
    0.22
    ä¸ĢçĤ¹åĦ¿
    0.22
    èĭĮ
    0.22
     blinking
    0.22
     Lambert
    0.22
    ä¹ĺ车
    0.22
    Activations Density 0.002%

    No Known Activations