© 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. 12130
    Prev
    Next
    INDEX
    Explanations

    appealing, attractive, or good attributes

    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
    fare
    -0.09
    obot
    -0.09
    eden
    -0.08
    åħ¬æŃ£
    -0.08
    irma
    -0.08
    ัà¸ĩ
    -0.08
     fen
    -0.08
    åĮĸçŁ³
    -0.08
    èµ³
    -0.08
    arro
    -0.08
    POSITIVE LOGITS
    æĭ¿æĿ¥
    0.10
    主æĦı
    0.10
    æĥ°
    0.09
    è°Ģ
    0.09
    çħŀ
    0.09
    oman
    0.09
    ORK
    0.09
    ibre
    0.09
    è§Ĵ
    0.09
    ä½ľä¸ºä¸Ģç§į
    0.08
    Activations Density 0.060%

    No Known Activations