© 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. 22406
    Prev
    Next
    INDEX
    Explanations

    scenic, scenery, picturesque descriptions

    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
    åĵĩ
    -0.09
    ses
    -0.09
    aby
    -0.09
     Bout
    -0.09
    å¼ıçļĦ
    -0.08
    çIJĨ解åĴĮ
    -0.08
    级åĪ«çļĦ
    -0.08
     cảnh
    -0.08
    身边çļĦ
    -0.08
    inator
    -0.08
    POSITIVE LOGITS
    RICT
    0.10
    trib
    0.10
    ãģĤãĤĭ
    0.10
    纶
    0.09
     enough
    0.09
    uste
    0.09
    建åħļ
    0.09
    uate
    0.09
     somew
    0.09
    家å±ħ
    0.09
    Activations Density 0.002%

    No Known Activations