© 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. 47810
    Prev
    Next
    INDEX
    Explanations

    performing actions or tasks

    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
    åİŁåĪĻ
    -0.10
    æķ¬ä¸ļ
    -0.08
    çłĶåıijæĬķåħ¥
    -0.08
    å°¾
    -0.08
    æĺ¯çĶ¨æĿ¥
    -0.08
     rentals
    -0.08
    å¾Ī好
    -0.08
    éĥ¨åĪĨåĨħ容
    -0.08
    alus
    -0.08
    ä¸Ģ个éĹ®é¢ĺ
    -0.08
    POSITIVE LOGITS
     tasks
    0.17
    æĵįä½ľ
    0.14
     actions
    0.14
    åĬ¨ä½ľ
    0.13
     operations
    0.13
     ìĪĺíĸī
    0.13
    çļĦåĬ¨ä½ľ
    0.13
    tasks
    0.13
     performed
    0.12
    ä»»åĭĻ
    0.12
    Activations Density 0.312%

    No Known Activations