© 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. 29895
    Prev
    Next
    INDEX
    Explanations

    toys and castles

    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
    çı¥
    -0.09
    kir
    -0.09
    踣
    -0.08
     Cer
    -0.08
    çijŁ
    -0.08
     quán
    -0.08
    æĭĶ
    -0.08
    黥
    -0.08
     SUN
    -0.08
     Kir
    -0.08
    POSITIVE LOGITS
    çİ©åħ·
    0.18
     toy
    0.12
     toys
    0.11
    ä¹IJåĽŃ
    0.11
    éģ¥æݧ
    0.11
    模åŀĭ
    0.10
    éĩįå¡ij
    0.10
    縮
    0.10
    æľ¨è´¨
    0.10
    models
    0.09
    Activations Density 0.116%

    No Known Activations