© 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. 34349
    Prev
    Next
    INDEX
    Explanations

    "well" followed by comma

    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
     obstruction
    -0.09
    elts
    -0.09
    夫人
    -0.08
    ç»ĩ
    -0.08
    注éĩį
    -0.08
    红æĺŁ
    -0.08
    éģįå¸ĥ
    -0.08
    èĥ½æī¾åĪ°
    -0.08
    æīĵ磨
    -0.08
    æ»ļæ»ļ
    -0.08
    POSITIVE LOGITS
    IDD
    0.09
    yo
    0.08
    well
    0.08
     well
    0.08
    imat
    0.08
    åĩī
    0.08
    çİ°å®ŀçĶŁæ´»
    0.08
    ately
    0.08
    ibox
    0.08
    å¨ģ
    0.08
    Activations Density 0.023%

    No Known Activations