© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2729
    Prev
    Next
    INDEX
    Explanations

    array declarations or buffer operations

    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
    Zoom
    -0.26
    .zoom
    -0.24
    ServiceProvider
    -0.24
    Dragging
    -0.23
    CompanyId
    -0.23
    .xticks
    -0.23
    .drag
    -0.23
    zoom
    -0.23
     долг
    -0.22
    (EXPR
    -0.22
    POSITIVE LOGITS
    æķ°ç»Ħ
    0.45
     arrays
    0.41
    éĺµ
    0.40
     array
    0.39
    array
    0.35
    arrays
    0.34
     Arrays
    0.34
    -array
    0.33
     ARRAY
    0.32
    Arrays
    0.32
    Activations Density 0.387%

    No Known Activations