© 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. 59419
    Prev
    Next
    INDEX
    Explanations

    PC

    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
    rema
    -0.10
    reme
    -0.09
    unte
    -0.09
    undi
    -0.09
    ün
    -0.09
    æĥ©
    -0.09
     Steak
    -0.09
    иде
    -0.09
     bouncing
    -0.09
     cardi
    -0.09
    POSITIVE LOGITS
    (PC
    0.09
     Barcl
    0.09
    å¼ĢåıijåĮº
    0.09
    æľī许å¤ļ
    0.09
    çķĢ
    0.08
    çīĸ
    0.08
    ttl
    0.08
    å°¼äºļ
    0.08
    ize
    0.08
    ees
    0.08
    Activations Density 0.217%

    No Known Activations