© 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. 37995
    Prev
    Next
    INDEX
    Explanations

    phrases starting with letters or "let"

    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
    çĤ¸å¼¹
    -0.10
    è£ĺ
    -0.10
    笳
    -0.09
    æıIJè®®
    -0.09
    ilde
    -0.09
    /apache
    -0.09
    为人
    -0.09
    好èݱåĿŀ
    -0.09
    croll
    -0.09
    orld
    -0.09
    POSITIVE LOGITS
    ia
    0.08
    æľĢ好æĺ¯
    0.08
    åĩºãģĹ
    0.07
     Coleman
    0.07
    è¦ģåĿļæĮģ
    0.07
     preferably
    0.07
    buch
    0.07
    ogen
    0.07
    Egypt
    0.07
    rang
    0.07
    Activations Density 1.149%

    No Known Activations