© 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. 17910
    Prev
    Next
    INDEX
    Explanations

    leaving or being left out

    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
    æĢ¯
    -0.10
    æ»ŀ
    -0.09
    ä¹łæĥ¯äºĨ
    -0.09
    æĬĢå·§
    -0.08
    çļĦä¹łæĥ¯
    -0.08
    æµģ失
    -0.08
    éĢĨåĬ¿
    -0.08
    éĢĨ
    -0.08
    身价
    -0.08
    æ¾Ħ
    -0.08
    POSITIVE LOGITS
     untouched
    0.12
    ville
    0.11
    å¹²é¢Ħ
    0.10
     buc
    0.10
    好好
    0.09
    å®īéĿĻ
    0.09
    讵
    0.09
    ä¸įåİ»
    0.09
    olib
    0.09
    gard
    0.09
    Activations Density 0.031%

    No Known Activations