© 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. 54216
    Prev
    Next
    INDEX
    Explanations

    activity, time, breaks

    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
    O
    -0.09
    pc
    -0.08
    HQ
    -0.08
    APH
    -0.08
    è¿Ļç§įæĥħåĨµ
    -0.08
    OI
    -0.08
    aal
    -0.08
    çļĦ第ä¸Ģ个
    -0.08
    ou
    -0.08
    é«ĺ端
    -0.08
    POSITIVE LOGITS
    è¡Įèµ°
    0.10
    .Apis
    0.10
    æİĢ
    0.09
     поÑģÑĤоÑı
    0.09
    .codec
    0.09
    glob
    0.09
    çłĶ究表æĺİ
    0.09
    家åĬ¡
    0.09
    ä»İäºĭ
    0.09
    次æķ°
    0.09
    Activations Density 0.059%

    No Known Activations