© 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. 53583
    Prev
    Next
    INDEX
    Explanations

    correspondence: corresponding to

    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
    ä¼IJ
    -0.11
    æ±ĤãĤģ
    -0.09
     bu
    -0.09
    alls
    -0.09
    serie
    -0.09
    åħ´èĩ´
    -0.09
     Asked
    -0.08
    ieri
    -0.08
    доÑĢ
    -0.08
    éĽ¾
    -0.08
    POSITIVE LOGITS
    对åºĶçļĦ
    0.22
    对åºĶ
    0.22
     corresponding
    0.20
     ÑģооÑĤвеÑĤÑģÑĤв
    0.19
    缸åºĶçļĦ
    0.18
     correspond
    0.16
    缸åºĶ
    0.15
     corresponds
    0.14
     Correspond
    0.14
     correspondent
    0.13
    Activations Density 0.180%

    No Known Activations