© 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. 27782
    Prev
    Next
    INDEX
    Explanations

    Bologna or similar sounding 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
    pisa
    -0.10
    æĪIJåĵģ
    -0.10
    .Disabled
    -0.09
    èĬ
    -0.09
     Bá
    -0.09
    èµĤ
    -0.09
    æµ®çİ°
    -0.08
    KeySpec
    -0.08
     AGRE
    -0.08
    鸾
    -0.08
    POSITIVE LOGITS
    æIJŃ
    0.10
    eden
    0.08
    çĿ¢
    0.08
    uai
    0.08
    ridge
    0.08
    éĽİ
    0.08
    çī¹æ´¾
    0.08
    åĶ±
    0.08
    尾巴
    0.08
    ç»ijæŀ¶
    0.08
    Activations Density 0.002%

    No Known Activations