© 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. 38858
    Prev
    Next
    INDEX
    Explanations

    shopping places

    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
    äºĨä¸Ģåı£
    -0.09
    ãĥĨãĥ¼ãĥ
    -0.09
    å°¼äºļ
    -0.09
    åİŁä¾Ĩ
    -0.09
    æĤ¬æµ®
    -0.09
    è¯ļå®ŀ
    -0.09
    å°ijçĪ·
    -0.08
    åİŁæĿ¥
    -0.08
    åİŁæĿ¥çļĦ
    -0.08
     Volk
    -0.08
    POSITIVE LOGITS
    _git
    0.09
    agram
    0.09
    idis
    0.08
     Copp
    0.08
     REGISTER
    0.08
    èĿī
    0.08
    ä¸įå¿ħ
    0.08
    .Tools
    0.08
    Digits
    0.08
    ëį°
    0.08
    Activations Density 0.002%

    No Known Activations