© 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. 54005
    Prev
    Next
    INDEX
    Explanations

    unrelated or separate

    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
    çłĶ究æĬ¥åijĬ
    -0.09
    说çļĦè¯Ŀ
    -0.09
    人å¿ĥ
    -0.09
    人æĢ§
    -0.09
    imenti
    -0.09
     СмоÑĤÑĢ
    -0.09
    .fac
    -0.08
    airy
    -0.08
    èĬ±åĽŃ
    -0.08
     еÑīÑij
    -0.08
    POSITIVE LOGITS
     unrelated
    0.24
    æĹłåħ³
    0.20
     ìłĦíĺĢ
    0.11
    æĹģ
    0.10
     ÑģовÑģем
    0.10
    åĩĮ
    0.09
    åħ¨ãģı
    0.09
     separate
    0.09
     Coll
    0.09
    çĭ¬ç«ĭ
    0.08
    Activations Density 0.079%

    No Known Activations