© 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. 18809
    Prev
    Next
    INDEX
    Explanations

    extracting addresses, names, or values

    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
    æĺ¯æľĢ好çļĦ
    -0.11
     wart
    -0.09
    èĨ³é£Ł
    -0.09
    ä¸įåħį
    -0.08
    lep
    -0.08
    常æĢģ
    -0.08
    é»ĺå¥ij
    -0.08
    æݥ轨
    -0.07
    çĨŁçŁ¥
    -0.07
    å¨ģåIJį
    -0.07
    POSITIVE LOGITS
    åľ¨è¿Ļ
    0.10
    çĶ¨äºĨ
    0.10
    engl
    0.09
    æĺİæĺ¾çļĦ
    0.09
    alus
    0.09
    æѧ
    0.09
    UNC
    0.09
    ä¸Ģç±»
    0.09
    ichi
    0.09
    æĭĨ
    0.09
    Activations Density 0.238%

    No Known Activations