© 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. 40100
    Prev
    Next
    INDEX
    Explanations

    fall in love or pregnant

    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
     Dude
    -0.09
    çIJĨ
    -0.08
    ovation
    -0.08
    ä¸įå®Į
    -0.08
    CHED
    -0.07
    ption
    -0.07
    ì´Ŀ
    -0.07
    trs
    -0.07
    æħİ
    -0.07
    å®Į
    -0.07
    POSITIVE LOGITS
    æĻļæĬ¥
    0.10
    ruk
    0.09
    stellen
    0.09
    ru
    0.09
    çİ°æľīçļĦ
    0.09
    inking
    0.09
    åİŁæľī
    0.09
    valu
    0.08
    æľīå¿ħè¦ģ
    0.08
    仨
    0.08
    Activations Density 0.003%

    No Known Activations