© 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. 10801
    Prev
    Next
    INDEX
    Explanations

    easy to

    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
     xúc
    -0.10
    acle
    -0.10
    ropol
    -0.09
    æĹłå£°
    -0.09
    ä¸įä½ı
    -0.09
    па
    -0.09
    åį±å®³
    -0.09
    oup
    -0.09
    awe
    -0.09
    ä¸įéĹ´
    -0.08
    POSITIVE LOGITS
    åıĪ好
    0.09
    ä½Ĩä¹Ł
    0.08
     bargain
    0.08
    åģļçļĦ
    0.08
    管çIJĨåĴĮ
    0.08
     sing
    0.08
    ÙĪار
    0.08
    cept
    0.07
    æĪŁ
    0.07
    èĢĮä¸Ķ
    0.07
    Activations Density 0.027%

    No Known Activations