© 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. 31096
    Prev
    Next
    INDEX
    Explanations

    top

    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
    PLICATION
    -0.09
    ä¹ı
    -0.08
    fully
    -0.08
    ä¹łä¿Ĺ
    -0.08
    ROS
    -0.08
    Translate
    -0.08
    å±Ĩ
    -0.08
    åİŁèijĹ
    -0.08
    ç¬ĥ
    -0.08
     Stoke
    -0.08
    POSITIVE LOGITS
    =top
    0.11
    ographical
    0.11
    ography
    0.10
    -notch
    0.10
    pling
    0.10
    (top
    0.10
    /top
    0.10
    èĥ½æī¾åĪ°
    0.09
     ÙĦدÙĬÙĨا
    0.09
    âĺĿ
    0.09
    Activations Density 0.087%

    No Known Activations