© 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. 30954
    Prev
    Next
    INDEX
    Explanations

    learning and training methods

    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
    ä¼ī
    -0.09
    è£ı
    -0.09
    æ¶Įçİ°
    -0.09
    è¿°
    -0.09
    TickCount
    -0.08
    ãģĵãģĿ
    -0.08
    olate
    -0.08
    olie
    -0.08
    渺
    -0.08
     Ancient
    -0.08
    POSITIVE LOGITS
    åħ»æĪIJ
    0.12
    è¯ķæİ¢
    0.11
    åѦåĪ°
    0.11
    è¯ķéªĮåĮº
    0.11
    è°ļ
    0.11
    积累
    0.11
    åѦä¼ļäºĨ
    0.11
     обÑĥÑĩ
    0.11
    ä¹łä¿Ĺ
    0.11
    éĵŃè®°
    0.10
    Activations Density 0.160%

    No Known Activations