© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27838
    Prev
    Next
    INDEX
    Explanations

    tiles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    Markup
    -0.09
    sted
    -0.09
    约å®ļ
    -0.09
     Weld
    -0.09
    .Visibility
    -0.09
     hb
    -0.09
    å·´å·´
    -0.09
    æ¹ĸåĮº
    -0.09
    æ±Łä¸ľ
    -0.08
    å¦Ĥä½ķåİ»
    -0.08
    POSITIVE LOGITS
    çĵ·çłĸ
    0.13
     tile
    0.11
     tiles
    0.11
     Tiles
    0.11
    èĥĮ
    0.10
     laid
    0.10
    _TILE
    0.10
    Tiles
    0.09
     showers
    0.09
     Tile
    0.09
    Activations Density 0.066%

    No Known Activations