© 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. 38427
    Prev
    Next
    INDEX
    Explanations

    part of something

    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
    ä¼ŀ
    -0.09
    æĻļ
    -0.08
     Fulton
    -0.08
    ft
    -0.08
    aison
    -0.08
    .FloatTensor
    -0.08
    è¦ģçľĭ
    -0.08
    æ¶Īè´¹éľĢæ±Ĥ
    -0.08
    bugs
    -0.08
    (ft
    -0.08
    POSITIVE LOGITS
    åıĤä¸İ
    0.15
    积æŀģåıĤä¸İ
    0.13
    åıĥèĪĩ
    0.12
     involvement
    0.12
    æľīåĬ©äºİ
    0.11
    åĬŁåĬ³
    0.11
    åıĤä¸İåĪ°
    0.11
    åĬ©æݨ
    0.11
    ä¿ĥæĪIJ
    0.10
    åĬ©åĬĽ
    0.10
    Activations Density 0.158%

    No Known Activations