© 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. 63757
    Prev
    Next
    INDEX
    Explanations

    melancholy and sadness

    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
    èĻĶ
    -0.10
    ä½ŀ
    -0.10
    æĥ¨
    -0.09
    æĦŁ
    -0.09
    _plain
    -0.08
    å¼ĢèĬ±
    -0.08
    çŁŃ线
    -0.08
    akens
    -0.08
    наÑĩен
    -0.08
    æĦıä¹īä¸ĬçļĦ
    -0.08
    POSITIVE LOGITS
    ä¹ĭ乡
    0.09
    stery
    0.09
    quet
    0.09
    身影
    0.09
    人å±ħ
    0.09
    fu
    0.09
    éĩįçĶŁ
    0.09
    ä¸ĸçķĮ第ä¸Ģ
    0.09
    .lu
    0.09
    人éĢī
    0.08
    Activations Density 0.003%

    No Known Activations