© 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. 1252
    Prev
    Next
    INDEX
    Explanations

    posted by, visitors, wrote, on patent

    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
    alone
    -0.27
    Facade
    -0.24
    rowData
    -0.23
    ordinate
    -0.23
    hood
    -0.23
    بÙĪÙĨ
    -0.22
    (skip
    -0.22
     cong
    -0.21
    lopedia
    -0.21
     ExecutionContext
    -0.21
    POSITIVE LOGITS
     penetrating
    0.26
    ças
    0.25
     META
    0.25
     mornings
    0.24
    IDL
    0.24
     penetr
    0.23
    ä»»ä½ķ人éĥ½
    0.23
     penet
    0.23
    ulner
    0.23
    Ļ¨
    0.22
    Activations Density 0.003%

    No Known Activations