© 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. 31663
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and following words

    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
    æ²IJ
    -0.09
    ually
    -0.09
    ulls
    -0.09
    elts
    -0.08
    .uk
    -0.08
    anks
    -0.08
    orse
    -0.08
    ors
    -0.08
    ologically
    -0.08
    æ²IJæµ´
    -0.08
    POSITIVE LOGITS
    æĤ«
    0.09
    娥
    0.08
    äºĽä»Ģä¹Ī
    0.08
    èĽĬ
    0.08
    devil
    0.08
    itte
    0.08
    ZA
    0.08
    çĩİ
    0.08
     Sang
    0.08
    åĬ²
    0.08
    Activations Density 0.089%

    No Known Activations