© 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. 40081
    Prev
    Next
    INDEX
    Explanations

    quantum dots

    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
    Not in Any Lists

    No Comments

    Negative Logits
    é»Ħéĩij
    -0.09
    oi
    -0.09
    mens
    -0.09
    麸
    -0.08
    zc
    -0.08
    éħįå¤ĩ
    -0.08
    ä¸Ĭä¸ĭ
    -0.08
    RequestBody
    -0.08
    _matched
    -0.08
    ypi
    -0.08
    POSITIVE LOGITS
    ä¸Ģé¢Ĺ
    0.12
    ç²Ĵ
    0.10
    迸
    0.09
    é¢Ĺ
    0.09
    çıł
    0.09
    æĺİçıł
    0.09
    èij«
    0.09
    æł¸å®ļ
    0.09
    åĬłåĢį
    0.09
     pearls
    0.09
    Activations Density 0.108%

    No Known Activations