© 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. 35427
    Prev
    Next
    INDEX
    Explanations

    topic of

    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
    楮
    -0.09
    licht
    -0.08
    cone
    -0.08
     ê°ľëħIJ
    -0.08
    ä¸Ģé¢Ĺ
    -0.08
    á»ĥu
    -0.08
    婵
    -0.08
     reck
    -0.08
    寨
    -0.08
    äºį
    -0.08
    POSITIVE LOGITS
    Ñĥй
    0.09
     пÑĢÑı
    0.09
    ilate
    0.09
     Äijẳng
    0.09
    åŃ°
    0.09
    ãģĮãĤī
    0.09
    请åģĩ
    0.08
    æĪij们è¦ģ
    0.08
    нал
    0.08
    апÑĢ
    0.08
    Activations Density 0.019%

    No Known Activations