© 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. 29399
    Prev
    Next
    INDEX
    Explanations

    also followed by verb

    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
    åĨµä¸Ķ
    -0.11
    渣
    -0.10
    æ±°
    -0.10
    æļĹæļĹ
    -0.09
    æĶ¾å¿ĥ
    -0.09
    .MODE
    -0.09
    omba
    -0.09
     oma
    -0.09
    模èĮĥ
    -0.09
    亢
    -0.09
    POSITIVE LOGITS
     neither
    0.09
    enberg
    0.08
    2
    0.08
    5
    0.08
     prior
    0.08
    åĵªå®¶
    0.08
    uy
    0.08
    3
    0.08
     Neither
    0.08
    4
    0.08
    Activations Density 0.059%

    No Known Activations