© 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. 53093
    Prev
    Next
    INDEX
    Explanations

    plug and socket connections

    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
    å¼Ĥ
    -0.10
    æĸĻ
    -0.10
    导èĪª
    -0.09
    æµļ
    -0.09
    ä¼łè¾¾
    -0.09
    жи
    -0.09
    éĨª
    -0.09
    éĻĭ
    -0.09
    utors
    -0.09
    éĩĬ
    -0.09
    POSITIVE LOGITS
    æĭĶ
    0.10
     plug
    0.09
    åħ¥åºĵ
    0.09
    çĩİ
    0.09
    jiang
    0.09
    æİ¥åĪ°
    0.08
    轻轻
    0.08
    лег
    0.08
    ãģķãģĪ
    0.08
    æĮĤåľ¨
    0.08
    Activations Density 0.235%

    No Known Activations