© 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. 17840
    Prev
    Next
    INDEX
    Explanations

    opener, finale, debut, or ending

    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
    ä¸įå®Į
    -0.11
    çłļ
    -0.10
    è¿Ļæł·ä¸Ģ
    -0.10
    fulness
    -0.09
    .za
    -0.09
    åĴĮ个人
    -0.09
    оз
    -0.08
    å¼ĢåıijåĪ©çĶ¨
    -0.08
    icamente
    -0.08
    åĪĿæľŁ
    -0.08
    POSITIVE LOGITS
     Thrones
    0.08
    aget
    0.08
     projections
    0.08
    Handled
    0.08
    ckett
    0.07
    å®ŀäºĭæ±Ĥæĺ¯
    0.07
    texts
    0.07
    synthesize
    0.07
    åĽłä¸º
    0.07
    头çĸ¼
    0.07
    Activations Density 0.008%

    No Known Activations