© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18457
    Prev
    Next
    INDEX
    Explanations

    donations and goods

    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
    idy
    -0.09
    åĬŀ
    -0.09
    æijĺ
    -0.09
    shaw
    -0.08
    ÙĬÙĨا
    -0.08
    charg
    -0.08
    èĤ²
    -0.07
    失误
    -0.07
    èµ¢
    -0.07
     hã
    -0.07
    POSITIVE LOGITS
    æįIJèµł
    0.14
    æįIJåĬ©
    0.12
    æįIJçĮ®
    0.12
     donations
    0.11
     donated
    0.11
    ç®±
    0.10
     donation
    0.10
    绵
    0.10
    ä¸Ŀ
    0.09
     Donation
    0.09
    Activations Density 0.028%

    No Known Activations