© 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. 6291
    Prev
    Next
    INDEX
    Explanations

    Dixieland jazz, Qix, Kix, Trixie, Wix

    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
    izations
    -0.09
    ../
    -0.09
    ship
    -0.09
    à¸Ļ
    -0.08
    æªĶ
    -0.08
    oled
    -0.08
    çIJ¥
    -0.08
    itet
    -0.08
    pees
    -0.08
    æŃ£åĵģ
    -0.08
    POSITIVE LOGITS
    tures
    0.12
    ãĢħ
    0.12
    alytics
    0.10
    ision
    0.10
    ëģĶ
    0.09
    lake
    0.09
    TURE
    0.09
    hift
    0.09
    èŁ¾
    0.09
    quare
    0.09
    Activations Density 0.006%

    No Known Activations