© 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. 57072
    Prev
    Next
    INDEX
    Explanations

    Cincinnati or Cynthia

    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
    liament
    -0.10
     Bris
    -0.09
    çķļ
    -0.09
    åĪ¹
    -0.09
    å¼ĢæľĹ
    -0.09
    веÑĢÑħ
    -0.09
    allen
    -0.08
    onom
    -0.08
    ocked
    -0.08
    ç¤ĵ
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.13
    çIJĽ
    0.10
    æĹ¥æĬ¥
    0.09
    äºĨå¾Īå¤ļ
    0.09
    éħ®
    0.09
    æĩ¦
    0.09
    ç³Ĭæ¶Ĥ
    0.08
    artz
    0.08
    urma
    0.08
    å¥ĺ
    0.08
    Activations Density 0.006%

    No Known Activations