© 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. 47473
    Prev
    Next
    INDEX
    Explanations

    with numbers and context

    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
    æĺİ天
    -0.10
    èŁł
    -0.10
    æĽ´è¦ģ
    -0.10
    otts
    -0.10
    oted
    -0.09
    èľ»
    -0.09
    è¿ĻåĦ¿
    -0.09
    RelativeTo
    -0.09
    ellen
    -0.09
    UDGE
    -0.09
    POSITIVE LOGITS
    ering
    0.09
    ãģ¶ãĤĬ
    0.08
    undi
    0.08
    ered
    0.08
    IfExists
    0.08
    è¿Ļç¬Ķ
    0.08
    çģ¿
    0.08
    TextNode
    0.07
    主人
    0.07
    éĵī
    0.07
    Activations Density 0.001%

    No Known Activations