© 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. 33581
    Prev
    Next
    INDEX
    Explanations

    plot and storyline details

    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
    碰
    -0.09
    ÑĮÑİ
    -0.09
    æĬ½è±¡
    -0.08
    âŁ¹
    -0.08
    æ°Ķè´¨
    -0.08
     Latina
    -0.08
    湿润
    -0.08
     Tropical
    -0.08
     Morm
    -0.08
     Prote
    -0.08
    POSITIVE LOGITS
    åī§æĥħ
    0.17
    æķħäºĭ
    0.13
     plot
    0.12
    主线
    0.11
     storyline
    0.11
    线索
    0.11
    éĺ´è°ĭ
    0.10
    /story
    0.10
     story
    0.10
    æĥħèĬĤ
    0.10
    Activations Density 0.051%

    No Known Activations