© 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. 22895
    Prev
    Next
    INDEX
    Explanations

    child's furniture and equipment

    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
    åIJĮåѦ们
    -0.10
    åĻĮ
    -0.09
    临
    -0.09
    çģ«çĥ§
    -0.09
    çĪ±ç¾İ
    -0.09
    æĭĪ
    -0.09
    è¿Ļè¾ĪåŃIJ
    -0.09
    é¢Ĩçķ¥
    -0.09
    åĩıèĤ¥
    -0.09
    scape
    -0.08
    POSITIVE LOGITS
    åŃ©åŃIJçļĦ
    0.22
    让åŃ©åŃIJ
    0.22
    对åŃ©åŃIJ
    0.22
    ç»ĻåŃ©åŃIJ
    0.20
    åŃ©åŃIJ
    0.19
    èĤ²åĦ¿
    0.18
    çİ©åħ·
    0.17
    家éķ¿
    0.17
     child
    0.17
    åĦ¿ç§ij
    0.16
    Activations Density 0.329%

    No Known Activations