© 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. 12247
    Prev
    Next
    INDEX
    Explanations

    pitcher or ester related 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
    Negative Logits
    èļģ
    -0.10
    姣
    -0.10
    oit
    -0.09
    athan
    -0.09
    enet
    -0.08
    Hints
    -0.08
    媳
    -0.08
    æĮijåīĶ
    -0.08
    eeee
    -0.08
    ¹
    -0.08
    POSITIVE LOGITS
    lish
    0.10
    åĬ¨æīĭ
    0.09
    交åıĭ
    0.09
    (es
    0.09
    anoi
    0.09
    åĮł
    0.09
    æľ¬äºº
    0.09
    ening
    0.09
    ãĥ³ãĤ°
    0.09
    umont
    0.09
    Activations Density 0.004%

    No Known Activations