© 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. 3420
    Prev
    Next
    INDEX
    Explanations

    handheld or mounted devices

    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
    lus
    -0.10
    liner
    -0.09
    èĨĽ
    -0.09
    HEST
    -0.09
    失è°ĥ
    -0.09
    emann
    -0.09
    çŃł
    -0.09
    樽
    -0.09
    .round
    -0.08
    åľ°ä¸ĭ室
    -0.08
    POSITIVE LOGITS
    å¼ı
    0.16
    å¼ıçļĦ
    0.16
    -style
    0.10
    å½¢å¼ı
    0.10
    å¤ļç§įå½¢å¼ı
    0.10
    åIJİèĢħ
    0.09
    -level
    0.09
    æłı
    0.09
    æĪIJåŀĭ
    0.09
    åħ¨èĥ½
    0.09
    Activations Density 0.186%

    No Known Activations