© 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. 62286
    Prev
    Next
    INDEX
    Explanations

    equality and rights for women

    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
    æıŃéľ²
    -0.11
    ãĥĹ
    -0.10
    追éļı
    -0.10
    缺åı£
    -0.09
    è°´è´£
    -0.09
    /feed
    -0.09
    å´´
    -0.09
    人åĬĽ
    -0.09
    æī¹åĪ¤
    -0.09
    éĤĪ
    -0.08
    POSITIVE LOGITS
    çļĦåľ°ä½į
    0.16
    åľ°ä½į
    0.13
    æѧè§Ĩ
    0.11
    å¾ħéģĩ
    0.10
     status
    0.10
     POV
    0.10
     Glass
    0.10
    åĩºè·¯
    0.09
    å¹³çŃī
    0.09
    å¾Ĺä¸įåĪ°
    0.09
    Activations Density 0.073%

    No Known Activations