© 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. 18844
    Prev
    Next
    INDEX
    Explanations

    cheering and support

    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
    殿åłĤ
    -0.11
    еÑĢÑĤ
    -0.10
    带走
    -0.10
    åħ¬åħ±èµĦæºIJ
    -0.10
    碰
    -0.10
    åįļä¼ļ
    -0.09
    egot
    -0.09
    çļĦåIJĪä½ľ
    -0.09
    çļĦ年轻人
    -0.08
    å²Ľå±¿
    -0.08
    POSITIVE LOGITS
    æĶ¯æĮģ
    0.16
    é¼ĵèĪŀ
    0.15
     support
    0.15
    åĬ©
    0.14
    é¼ĵåĬ±
    0.14
    Support
    0.14
     Support
    0.14
    åĬłæ²¹
    0.13
    æĶ¯æĮģåĬĽåº¦
    0.13
    support
    0.13
    Activations Density 0.203%

    No Known Activations