© 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. 23988
    Prev
    Next
    INDEX
    Explanations

    not understand

    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
    å¤ĸå¥Ĺ
    -0.10
    æĺİçŁ¥
    -0.09
    箪
    -0.09
    ä¸ĺ
    -0.09
    çļĦä¸Ģåijĺ
    -0.09
     Lat
    -0.08
    atin
    -0.08
    å¿įåıĹ
    -0.08
    ãģ¨ãĤĬ
    -0.08
     bite
    -0.08
    POSITIVE LOGITS
    èĩªåĬ©
    0.11
    à¹Ģà¸Ńà¸ĩ
    0.10
    èĩªè¡Į
    0.10
     alone
    0.10
    åĬ¬
    0.09
    alone
    0.09
    lasses
    0.09
    èĩªæķij
    0.09
    å·½
    0.09
    æīĭå·¥
    0.09
    Activations Density 0.036%

    No Known Activations