© 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. 63926
    Prev
    Next
    INDEX
    Explanations

    about

    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
    Nil
    -0.08
    /community
    -0.08
    ippi
    -0.08
    à¸ģรà¸ĵ
    -0.08
    çĻ¾å®¶
    -0.08
    æѧ
    -0.08
    åĮħ袱
    -0.08
    sky
    -0.08
    estic
    -0.08
     toute
    -0.07
    POSITIVE LOGITS
    èĤ¡æĿĥæĬķèµĦ
    0.09
    说çĿĢ
    0.09
    åıijæĮ¥
    0.09
    /from
    0.08
    aston
    0.08
    縱
    0.08
    ifest
    0.08
    urator
    0.08
    ä¸ĢçĤ¹åĦ¿
    0.08
    lying
    0.08
    Activations Density 0.039%

    No Known Activations