© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9998
    Prev
    Next
    INDEX
    Explanations

    he 'll

    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
    sWith
    -0.12
    mente
    -0.11
    -minded
    -0.11
    nya
    -0.11
    è¿Ļæł·çļĦè¯Ŀ
    -0.10
    ness
    -0.10
    æĢ§å¼º
    -0.09
    adies
    -0.09
    ’
    -0.09
    keit
    -0.09
    POSITIVE LOGITS
    /she
    0.20
    /her
    0.19
    èĢģ人家
    0.18
    -même
    0.15
    zelf
    0.15
    /th
    0.12
    aviest
    0.12
    ä¿©
    0.12
    çļĦ人çĶŁ
    0.11
    ×Ļ׾
    0.10
    Activations Density 0.121%

    No Known Activations