© 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. 33938
    Prev
    Next
    INDEX
    Explanations

    3GPP LTE

    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®ĸ
    -0.10
    çļĦ第ä¸Ģ个
    -0.09
    ulp
    -0.09
    tractor
    -0.09
    ÑĪки
    -0.08
    uell
    -0.08
    æĹłåı¯
    -0.08
    èĥ
    -0.08
     gr
    -0.08
    çļĦèīºæľ¯
    -0.08
    POSITIVE LOGITS
    ä¹İ
    0.09
    大åıij
    0.09
    æĮij
    0.09
    棣
    0.08
    .Misc
    0.08
    .NET
    0.08
    éĻĭ
    0.08
    å¸ĥç½®
    0.08
    级以ä¸Ĭ
    0.08
    楽
    0.08
    Activations Density 0.001%

    No Known Activations