© 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. 23446
    Prev
    Next
    INDEX
    Explanations

    there 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
    ise
    -0.09
    å®ı
    -0.08
    éķĿ
    -0.08
     Rising
    -0.08
    åįģ足
    -0.08
    亡
    -0.08
    åIJĪ
    -0.08
    лоÑĤ
    -0.08
    imer
    -0.08
    æļĹ
    -0.07
    POSITIVE LOGITS
    åľ¨éĤ£éĩĮ
    0.14
    éĤ£åĦ¿
    0.13
    éĤ£éĩĮ
    0.12
    è¿Ľåİ»
    0.12
     perman
    0.11
    ä¸Ĭåİ»
    0.11
    Ä°L
    0.10
    éĤ£æł·
    0.10
    ãģĿãģĵãģ«
    0.10
     proprié
    0.10
    Activations Density 0.089%

    No Known Activations