© 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. 47594
    Prev
    Next
    INDEX
    Explanations

    gotten way, gotten most, gotten better

    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
    side
    -0.12
    eenth
    -0.11
    å®ļäºĨ
    -0.10
    ted
    -0.10
    sWith
    -0.10
    ollen
    -0.09
    sets
    -0.09
    äºĨ个
    -0.09
    çĤ¹å¤ļ
    -0.09
    çĶ¨å·¥
    -0.09
    POSITIVE LOGITS
    à¹Į
    0.11
    ergy
    0.09
    naires
    0.09
    Ùī
    0.09
    naire
    0.09
    {}",
    0.09
    zym
    0.08
    eric
    0.08
    ally
    0.08
    ews
    0.08
    Activations Density 0.017%

    No Known Activations