© 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. 10863
    Prev
    Next
    INDEX
    Explanations

    out of the

    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
    åĵªåĦ¿
    -0.10
     outcome
    -0.10
    æĸ¹åľĨ
    -0.09
    æĦıä¹īä¸ĬçļĦ
    -0.09
    outcome
    -0.09
    éĤ£æŶåĢĻ
    -0.09
    åĬŁåĬĽ
    -0.09
    ark
    -0.09
    immel
    -0.09
    æĺİçĻ½äºĨ
    -0.08
    POSITIVE LOGITS
    icina
    0.10
    è¿İ
    0.10
     ÙĪعÙĨ
    0.10
    侧éĿ¢
    0.09
    reach
    0.09
    å½ĵãģŁãĤĬåīį
    0.09
    åħ±åIJĮåıijå±ķ
    0.09
    éļIJå½¢
    0.09
    .getvalue
    0.09
    寻常
    0.09
    Activations Density 0.045%

    No Known Activations