© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60660
    Prev
    Next
    INDEX
    Explanations

    how to achieve this

    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
    Negative Logits
     noop
    -0.08
    çĭĹ
    -0.08
    æĤ£
    -0.08
    å²ij
    -0.08
    åĢŁæѤ
    -0.08
    å®Įåħ¨åı¯ä»¥
    -0.08
    quat
    -0.08
    .htm
    -0.08
     quarters
    -0.08
    以æѤ
    -0.08
    POSITIVE LOGITS
    åģļåĪ°
    0.14
     accomplished
    0.13
    è¦ģåģļåĪ°
    0.13
     accomplish
    0.12
    æĹĮ
    0.11
    åģļä¸įåĪ°
    0.11
    为ä¹ĭ
    0.09
    ãĤ«ãĥ©ãĥ¼
    0.09
     пÑĥÑĤ
    0.09
    åģļåĪ°äºĨ
    0.09
    Activations Density 0.125%

    No Known Activations