© 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. 21898
    Prev
    Next
    INDEX
    Explanations

    strategic planning

    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
    累累
    -0.11
    æīĵæ³ķ
    -0.10
    åİĨåı²æĢ§
    -0.10
    æĪijå¸ĮæľĽ
    -0.09
    天涯
    -0.09
    人家
    -0.09
    åĬŁæķĪ
    -0.09
    æıŃ
    -0.09
    大æĪ·
    -0.09
    æĪij没æľī
    -0.09
    POSITIVE LOGITS
     planning
    0.09
     Planning
    0.09
    è§ĦåĪĴ
    0.09
    æħİ
    0.09
     Dank
    0.09
     Parenthood
    0.08
    Planning
    0.08
     planners
    0.08
    .exchange
    0.08
    sic
    0.08
    Activations Density 0.018%

    No Known Activations