© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10393
    Prev
    Next
    INDEX
    Explanations

    links in html

    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
    æ¯ģ
    -0.11
    åĪĨå·¥
    -0.11
    éĿ¢åŃĶ
    -0.10
    äºĮåŃĹ
    -0.10
    å¯ĨéĽĨ
    -0.10
    erce
    -0.10
    rub
    -0.10
    è¿ĺæľīä¸ĢäºĽ
    -0.10
    ä¹Łæľīä¸ĢäºĽ
    -0.10
    åıįåĵį
    -0.09
    POSITIVE LOGITS
    oste
    0.08
    LER
    0.08
    iday
    0.07
    IVA
    0.07
    å¿ĥ仪çļĦ
    0.07
    dong
    0.07
    æŁIJ
    0.07
    æŁIJ个
    0.07
     previous
    0.07
    gan
    0.07
    Activations Density 0.525%

    No Known Activations