© 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. 3289
    Prev
    Next
    INDEX
    Explanations

    creating, managing, offering, finding

    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
    æѤåĪ»
    -0.10
    oling
    -0.10
    ä¼ļç»Ļ
    -0.10
    åħ¶æīĢ
    -0.10
    alyze
    -0.10
    è¦ģ说
    -0.09
    imize
    -0.09
    å°±å¦ĤåIJĮ
    -0.09
    apping
    -0.09
    åı¯ä»¥è¯´
    -0.09
    POSITIVE LOGITS
     being
    0.16
     having
    0.13
    being
    0.13
     becoming
    0.11
     getting
    0.10
     finding
    0.10
    å¼Ģå±ķ
    0.10
     making
    0.10
    æĬĬ
    0.10
     seeing
    0.10
    Activations Density 0.813%

    No Known Activations