© 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. 578
    Prev
    Next
    INDEX
    Explanations

    multiple items or parts

    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¸ĩ
    -0.24
    åįĥå¹´
    -0.24
    -rich
    -0.22
     Atl
    -0.22
    CCA
    -0.22
    fiber
    -0.22
     thousands
    -0.22
     millions
    -0.22
     nanop
    -0.22
    illon
    -0.22
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.40
     multiple
    0.34
    å¤ļ个
    0.32
    å¤ļéĩį
    0.30
     included
    0.29
     listed
    0.29
    ä¾Ŀ次
    0.28
     Multiple
    0.28
    éĢIJä¸Ģ
    0.27
    multiple
    0.26
    Activations Density 0.443%

    No Known Activations