© 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. 61750
    Prev
    Next
    INDEX
    Explanations

    abandonment, deserted, defaulted, fled

    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¯ĵ
    -0.09
    缴åĪ°
    -0.09
     fer
    -0.09
    å¥ł
    -0.09
    积累
    -0.09
    ä¸ī人
    -0.09
    éĢģä¸Ĭ
    -0.09
    çĻ½è¡£
    -0.09
    weed
    -0.09
    ä¹Łåıªèĥ½
    -0.09
    POSITIVE LOGITS
    éĢĥéģ¿
    0.16
    éĢĥè·ij
    0.13
    éĢĥ离
    0.13
    éĢĥ
    0.11
    å¼ĥ
    0.11
     bá»ı
    0.11
    éĢĥèĦ±
    0.11
    æ£Ħ
    0.10
     esc
    0.10
    è¿Ŀ约
    0.10
    Activations Density 0.115%

    No Known Activations