© 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. 36414
    Prev
    Next
    INDEX
    Explanations

    first time things happened

    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
    çIJı
    -0.09
    éļıæŶ
    -0.09
    æıĨ
    -0.08
    ä¸įä»ħèĥ½
    -0.08
    ä¸įä½Ĩ
    -0.08
    à¹Ĥม
    -0.08
    æĽ´å¤ļçļĦæĺ¯
    -0.08
    è¾Ľ
    -0.08
    gar
    -0.08
    åĩłç§į
    -0.08
    POSITIVE LOGITS
    heel
    0.10
    è¿Ļä¹Īå¤ļ
    0.09
    iali
    0.09
    åıĤ
    0.09
    ourd
    0.09
    è¿Ļä¹Ī大
    0.09
     Corey
    0.08
    èĪĴ
    0.08
    ruk
    0.08
    æĥ³åĪ°äºĨ
    0.08
    Activations Density 0.029%

    No Known Activations