© 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. 5727
    Prev
    Next
    INDEX
    Explanations

    Getty Images

    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
    kk
    -0.08
    åĶ¯
    -0.08
    æŁ¢
    -0.08
    tures
    -0.08
    most
    -0.08
    rous
    -0.07
    æĹłæķĮ
    -0.07
    ão
    -0.07
    ithe
    -0.07
    up
    -0.07
    POSITIVE LOGITS
    yne
    0.09
    åħ¬æĬ¥
    0.09
     Giov
    0.09
    usch
    0.09
    ittel
    0.09
    UGH
    0.08
     hÆ°á»Łng
    0.08
    å¦Ĭ
    0.08
    é¬ĵ
    0.08
    adan
    0.08
    Activations Density 0.005%

    No Known Activations