© 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. 61756
    Prev
    Next
    INDEX
    Explanations

    domain names and URLs

    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
    elden
    -0.09
    atches
    -0.09
    etical
    -0.09
     cle
    -0.08
    adi
    -0.08
    空åīį
    -0.08
    irst
    -0.08
    raq
    -0.08
    hung
    -0.08
    ä¸ı
    -0.08
    POSITIVE LOGITS
    åĢ¦
    0.10
    å§Ķ
    0.09
    æݾ
    0.09
    稷
    0.09
    coal
    0.08
    沦
    0.08
    ä¸ĢåĪĩ
    0.08
    PLUS
    0.08
    æĪĽ
    0.08
     sud
    0.08
    Activations Density 0.486%

    No Known Activations