© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6838
    Prev
    Next
    INDEX
    Explanations

    wetlands and areas

    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
     swept
    -0.09
    æ·ij
    -0.08
    ToFit
    -0.08
     Rap
    -0.08
     Fut
    -0.08
    ters
    -0.08
    ellas
    -0.08
    onest
    -0.08
    åIJŀ
    -0.08
    ucs
    -0.08
    POSITIVE LOGITS
    æ²¼
    0.11
    æĮĩ示
    0.09
    anford
    0.09
    æ´Ħ
    0.09
     Burk
    0.09
    .managed
    0.09
    äºı
    0.09
    ë²Ī
    0.09
     benefici
    0.09
    补水
    0.09
    Activations Density 0.059%

    No Known Activations