© 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. 24158
    Prev
    Next
    INDEX
    Explanations

    a.k.a. or a/k/a aliases

    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
    åĿļ强
    -0.10
    ations
    -0.09
    ä¸įäºĨ
    -0.09
     sourceMapping
    -0.09
    çħ¤
    -0.09
    intel
    -0.08
    积æŀģæĢ§
    -0.08
    表çĻ½
    -0.08
    acier
    -0.08
    ance
    -0.08
    POSITIVE LOGITS
    溢
    0.08
    èģĮ
    0.08
    illet
    0.08
    offs
    0.08
    down
    0.08
     gift
    0.08
    otti
    0.08
    å¸ĮæľĽå¤§å®¶
    0.08
    CurrentUser
    0.08
     equal
    0.08
    Activations Density 0.018%

    No Known Activations