© 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. 32404
    Prev
    Next
    INDEX
    Explanations

    Milford and Dover

    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
    æĸ¥
    -0.09
    èĢħçļĦ
    -0.09
    人士
    -0.09
    æĸ¯åŁº
    -0.09
    çĤĶ
    -0.09
    ement
    -0.08
    çīĮ
    -0.08
     bothering
    -0.08
    åݿ级
    -0.08
    ult
    -0.08
    POSITIVE LOGITS
     tụ
    0.09
    UCT
    0.09
    ChildIndex
    0.09
    PEAR
    0.09
    é»ı
    0.09
    æ´
    0.09
    ondo
    0.08
    IRR
    0.08
    uct
    0.08
    à¦ĵ
    0.08
    Activations Density 0.003%

    No Known Activations