© 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. 18499
    Prev
    Next
    INDEX
    Explanations

    accomplish task done

    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
     Sundays
    -0.08
    uib
    -0.08
    å¥Ĺè£ħ
    -0.08
    è¿Ķè¿ĺ
    -0.08
     Salv
    -0.08
    onica
    -0.08
    ä¸Ģä¸ĭ
    -0.08
     bingo
    -0.08
    DIM
    -0.08
    çĻ¾å¼º
    -0.08
    POSITIVE LOGITS
    ä»»åĬ¡
    0.15
    å®ĮæĪIJ
    0.15
     done
    0.14
    ä»»åĭĻ
    0.14
     task
    0.14
     tasks
    0.14
     accomplish
    0.13
     accomplished
    0.13
     Done
    0.13
    å®ĮæĪIJäºĨ
    0.12
    Activations Density 0.052%

    No Known Activations