© 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. 11308
    Prev
    Next
    INDEX
    Explanations

    a single

    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
    å°¾
    -0.10
    æīįæĺ¯çľŁæŃ£
    -0.10
    鬼
    -0.10
    ä¹Łæĺ¯ä¸Ģç§į
    -0.09
    holm
    -0.09
    éĢIJ
    -0.09
    æŁIJç§į
    -0.09
     tail
    -0.09
    娥
    -0.09
    çIJIJ
    -0.09
    POSITIVE LOGITS
     اÙĦÙĪاØŃد
    0.15
    ä¸Ģé¡¿
    0.11
    ä¸Ģ个
    0.10
    ä¸Ģæł¹
    0.09
    ãģĤãģŁãĤĬ
    0.09
    ä¸ĢæĿ¯
    0.09
    LEAN
    0.08
    ä¸ĢåĿĹ
    0.08
    unei
    0.08
    ssf
    0.08
    Activations Density 0.098%

    No Known Activations