© 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. 704
    Prev
    Next
    INDEX
    Explanations

    as ... as

    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
    æĽ´å¤ļ
    -0.25
    Fluid
    -0.23
    cid
    -0.23
    ä¸Ģ款
    -0.23
    主æĮģ人
    -0.22
    大åĨĽ
    -0.22
    çļĦä¸ĢåĪĩ
    -0.22
    IMS
    -0.21
    Storm
    -0.21
    ful
    -0.21
    POSITIVE LOGITS
     early
    0.26
     December
    0.26
    pects
    0.25
     January
    0.24
     August
    0.23
     February
    0.23
    åħ¬åħĥåīį
    0.23
     September
    0.23
    é
    0.22
     October
    0.22
    Activations Density 0.011%

    No Known Activations