© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 64134
    Prev
    Next
    INDEX
    Explanations

    movement around

    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
    Negative Logits
    èµı
    -0.10
    essler
    -0.10
    è¿Ļ个èģĮä¸ļ
    -0.09
    è¿¢
    -0.09
    /arch
    -0.09
    ÑģÑĤи
    -0.09
    èĢķ
    -0.09
    讣
    -0.09
    å¾ģéĽĨ
    -0.09
    è³ŀ
    -0.09
    POSITIVE LOGITS
    æľīå¿ħè¦ģ
    0.09
    amber
    0.09
    onus
    0.08
    SIDE
    0.08
    pard
    0.08
    iox
    0.08
    åĬªåĬĽ
    0.08
    nex
    0.08
    enticate
    0.08
    æīĭåĨĮ
    0.08
    Activations Density 0.021%

    No Known Activations