© 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. 40018
    Prev
    Next
    INDEX
    Explanations

    users, customers, clients, tenants

    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
    ä¸Ģåı¥è¯Ŀ
    -0.09
     staffers
    -0.09
    åĿĢ
    -0.09
    èĥ½åIJ¦
    -0.08
    ä¸Ģ款
    -0.08
    .Resources
    -0.08
    iete
    -0.08
    å·«
    -0.08
    åĵģå¾·
    -0.08
    è£Ĥ
    -0.08
    POSITIVE LOGITS
    大æĪ·
    0.14
    使çĶ¨èĢħ
    0.12
    åĩłå®¶
    0.12
    çĶ¨æ°´
    0.11
    å®ŀä½ĵ
    0.10
    demand
    0.10
    çļĦéľĢæ±Ĥ
    0.10
    客æĪ·çļĦ
    0.10
    çĶ¨äººåįķä½į
    0.10
     demand
    0.10
    Activations Density 0.141%

    No Known Activations